Showing 1–50 of 268 results for author: Han, P

Fault Diagnosis of Dynamic Systems Under Unknown Operating Conditions: A Condition-Guided Selective Adaptation Approach

Authors: Jiaming Liu, Zeyi Liu, Hongshuo Zhao, Pengyu Han, Xiao He

Abstract: Fault diagnosis under unknown operating conditions remains challenging for dynamic industrial systems, as the distribution shift caused by changing operating conditions can significantly degrade the performance of diagnostic models in real-world applications. To address the problem, a condition-guided selective adaptation approach is proposed. Specifically, a novel continuous operating-condition a… ▽ More Fault diagnosis under unknown operating conditions remains challenging for dynamic industrial systems, as the distribution shift caused by changing operating conditions can significantly degrade the performance of diagnostic models in real-world applications. To address the problem, a condition-guided selective adaptation approach is proposed. Specifically, a novel continuous operating-condition adversarial learning strategy with progressive training is developed in the offline stage to enhance the generalization ability of the diagnostic model. During online deployment, residual operating-condition responses are exploited to identify reliable unlabeled samples from streaming data, which are then used to update the diagnostic model. Extensive experiments on real-world gearbox and motor datasets have demonstrated that the proposed framework outperforms state-of-the-art methods in diagnostic accuracy while maintaining relatively low test-time, showing its potential for practical industrial applications. △ Less

Submitted 21 August, 2026; originally announced August 2026.

Adaptive Heterogeneous Compression for Resource-Efficient Federated Knowledge Distillation

Authors: Chenwang Liu, Yijun Liu, Chang Liu, Xu Zhang, Pengchao Han

Abstract: Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge. Federated knowledge distillation (FedKD) alleviates model heterogeneity by combining prototype-wise parameter aggregation and knowledge transfer across heterogeneous models. However, transmitting gradients… ▽ More Federated learning (FL) enables privacy-preserving distributed model training but faces challenges from heterogeneous model architectures and limited communication resources at the network edge. Federated knowledge distillation (FedKD) alleviates model heterogeneity by combining prototype-wise parameter aggregation and knowledge transfer across heterogeneous models. However, transmitting gradients still introduces considerable communication overhead, while existing compression approaches typically apply a uniform strategy across clients and ignore their diverse model characteristics and resource capacities. To address this issue, we propose a heterogeneous compression framework for FedKD that enables each client to select a compression strategy from a candidate strategy set. We formulate the compression strategy selection problem as a non-stationary stochastic multi-armed bandit (MAB), where each arm corresponds to a compression strategy. An efficiency-aware reward is designed by jointly considering local optimization improvement, global knowledge alignment, and execution time. Based on this formulation, we develop an Adaptive heterogeneouS Compression algorithm for fEderated kNowledge Distillation (ASCEND), which employs an exponential moving average (EMA)-enhanced $ε$-greedy policy to balance exploration and exploitation. Experimental results on multiple datasets demonstrate that ASCEND effectively adapts to heterogeneous model and resource settings, reducing communication overhead and training time while maintaining competitive model accuracy. △ Less

Submitted 16 August, 2026; originally announced August 2026.

Modular Cognitive Architecture Emerges in Large Language Models

Authors: Pengrui Han, Jacob Andreas, Evelina Fedorenko, Andrea Gregor de Varda

Abstract: The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organizati… ▽ More The human brain exhibits a striking degree of functional specialization, with distinct networks supporting language, formal reasoning, reasoning about other minds, and reasoning about the physical world. Is this modular organization a fundamental principle of how intelligent systems must be built, or an evolutionary accident specific to biological brains? Here, we test whether a similar organization emerges in Large Language Models--another class of intelligent systems created through a very different optimization process. Using circuit analyses across N=46 tasks spanning four cognitive domains (language, formal reasoning, social reasoning, physical reasoning), we find that LLMs develop a modular architecture that mirrors the human brain: tasks drawing on the same network in humans recruit overlapping neurons in LLMs, whereas tasks drawing on different networks recruit distinct neurons. The convergent emergence of modularity in brains and neural networks suggests that it may be a fundamental property of intelligent systems. △ Less

Submitted 26 June, 2026; originally announced August 2026.

Comments: https://pengrui-han.github.io/LLM_Modularity_Page/

SynAct: A Reasoning-Acting Large Language Model Agent for Adaptive Synthesis Optimization

Authors: Fangzhou Liu, Peiyi Han, Jiawei Liu, Yuan Pu, Zhuolun He, Rongliang Fu, Tsung-Yi Ho, Bei Yu

Abstract: Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which… ▽ More Logic synthesis transforms RTL designs into gate-level netlists, where PPA results are highly sensitive to the choice of optimization commands, making synthesis tuning both high-dimensional and expensive. Previous approaches fall into two categories: automated methods, which perform black-box search over fixed action spaces with limited decision-level interpretability, and LLM-based methods, which typically generate static scripts upfront and cannot adapt to evolving circuit states. We present SynAct, an adaptive closed-loop LLM reasoning--acting agent that iteratively diagnoses live synthesis reports and reasons over the current circuit state, retrieved tool knowledge, and historical optimization experience to issue targeted commands. SynAct focuses on improving timing, particularly worst negative slack (WNS), while maintaining balanced area and power trade-offs. Experiments on a commercial synthesis tool across 14 designs show that SynAct reduces average WNS to 27% of that from bootstrap synthesis. △ Less

Submitted 13 August, 2026; v1 submitted 12 August, 2026; originally announced August 2026.

Comments: 12 pages, 8 figures

Macaron-V1: Towards Open Continual Learning with Self-Improvement and Mixture-of-LoRA

Authors: Mind Lab, :, Vin Bo, Asher Cai, Jingwei Cao, Song Cao, Vic Cao, Amelia Chen, Andrew Chen, Kaijie Chen, Cleon Cheng, Steven Chiang, Kaixuan Fan, Hera Feng, Huan Feng, Arthur Fu, Jun Gao, Pyke Han, Nolan Ho, Ori Hong, Hailee Hou, Piers Hua, Charles Huang, Miles Jiang, Nora Jiang , et al. (52 additional authors not shown)

Abstract: Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized around two system goals. Adaptation is pursued through recursive improvement of versioned model-harness pairs, where experience from one configuration is evaluated under an external contract and used to construct its success… ▽ More Macaron-V1 is an open agent-model family for experiential intelligence: learning from experience in real environments and continuing to learn after deployment. It is organized around two system goals. Adaptation is pursued through recursive improvement of versioned model-harness pairs, where experience from one configuration is evaluated under an external contract and used to construct its successor. Collaboration is pursued via the Mixture-of-LoRA (MoL) architecture that freezes a base model, composes specialist LoRA adapters, and selects one LoRA per user turn. The flagship Macaron-V1-Venti combines a 744B GLM-5.2 base with four LoRAs for chat, agent, coding, and GenUI; the Qwen3.6-based Macaron-V1-Tall (50B) uses the same design for local deployment. This report presents Macaron-V1 as a co-designed system spanning architecture, algorithms, and infrastructure. The MoL architecture supports continual learning through extensible LoRA specialists. The algorithm combines Model-Harness Co-design and recursive self-improvement loop, including the UI4A component-native GenUI harness, a stateful action substrate, versioned HCP contract, and the agentic RL framework MindForge. The supporting infrastructure includes the post-training platform MinT, the long-context RL method LongStraw, and stability techniques for sparse MoE and DSA base models. We evaluate Macaron-V1 on Personal Intelligence, GenUI, and general capability benchmarks against frontier baselines. Our results validate the current system, while compounding gains from continual learning and collective intelligence remain open questions. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Comments: 49 pages, technical report

Coordinate-Residual Physics-Driven Neural Network for Electromagnetic Inverse Scattering

Authors: Yutong Du, Zicheng Liu, Bo Qi, Yali Zong, Peixian Han

Abstract: Electromagnetic inverse scattering is a nonlinear and ill-posed problem, where accurate reconstruction is challenging due to measurement limitations, noise, and high computational costs, especially for 3-D imaging. Although physics-driven neural networks (PDNNs) reduce the dependence on labeled training data, existing accelerated PDNN frameworks often rely on preliminary reconstruction-based regio… ▽ More Electromagnetic inverse scattering is a nonlinear and ill-posed problem, where accurate reconstruction is challenging due to measurement limitations, noise, and high computational costs, especially for 3-D imaging. Although physics-driven neural networks (PDNNs) reduce the dependence on labeled training data, existing accelerated PDNN frameworks often rely on preliminary reconstruction-based region selection, which may introduce instability when the selected region is inaccurate. In this paper, a coordinate-residual physics-driven neural network (CRPDNN) is proposed for 3-D electromagnetic inverse scattering. The proposed solver directly reconstructs the unknown contrast distribution using normalized spatial coordinates and a residual convolutional network, without requiring a preliminary reconstruction. For the reported noise-free 3-D synthetic cases, CRPDNN achieves an average relative error of 2.10\%, compared with 7.97\% for CSI and 3.99\% for $L_{2/3}$-FBE-WCIE, while providing approximately 5.5- and 12.1-fold speedups over the two baselines, respectively. Supplementary 2-D comparisons further confirm its stability and computational efficiency relative to existing PDNN frameworks. CRPDNN also maintains reliable reconstruction performance under noisy measurements, and the 3-D Fresnel experiments further indicate its potential for practical imaging applications. The related code is available at https://github.com/Physics-driven-methods. △ Less

Submitted 10 August, 2026; originally announced August 2026.

Anisotropic Particle Transport from a Pulsar Wind Nebula Revealed by Einstein Probe and LHAASO

Authors: Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao, D. Bastieri, X. J. Bi, Y. J. Bi, W. Bian, J. Blunier, A. V. Bukevich, C. M. Cai, W. Y. Cao, Zhe Cao, J. Chang, J. F. Chang, E. S. Chen, G. H. Chen, H. K. Chen, L. F. Chen, Liang Chen, Long Chen, M. J. Chen, M. L. Chen, Q. H. Chen, S. Chen , et al. (320 additional authors not shown)

Abstract: Pulsar wind nebulae (PWNe) are major cosmic ray accelerators, yet the mechanisms transporting high-energy particles into the interstellar medium remain elusive. Building on the LHAASO discovery of an ultra-high-energy (UHE) $γ$-ray source near the bow-shock PWN powered by the pulsar PSR J1740+1000, we present a joint Einstein Probe (EP) and LHAASO study of this system. EP observations reveal an ex… ▽ More Pulsar wind nebulae (PWNe) are major cosmic ray accelerators, yet the mechanisms transporting high-energy particles into the interstellar medium remain elusive. Building on the LHAASO discovery of an ultra-high-energy (UHE) $γ$-ray source near the bow-shock PWN powered by the pulsar PSR J1740+1000, we present a joint Einstein Probe (EP) and LHAASO study of this system. EP observations reveal an extended X-ray tail far exceeding the structure previously seen by XMM-Newton. Updated LHAASO observations show that the $γ$-ray emission is elongated, with its major axis aligned with the extended X-ray tail revealed by EP. This is the first detection of an X-ray pulsar tail associated with a spatially coincident extended UHE $γ$-ray emission. The X-ray and $γ$-ray spectrum can be well explained with a single population of relativistic electrons via synchrotron and inverse Compton radiation, respectively, removing the need for particle re-acceleration during propagation. The results unambiguously show that electrons/positrons above 100 TeV are escaping from the PWN. Instead of the immediate, isotropic diffusion into ambient interstellar medium that is typically assumed, these particles are transported anisotropically over at least $\sim$10 pc, either guided by the background magnetic field or carried by an advective outflow. △ Less

Submitted 7 August, 2026; originally announced August 2026.

Comments: Accepted by Science China Physics, Mechanics, and Astronomy. Main text: 9 pages, 4 figures, 1 table; Supplementary Materials: 7 pages, 2 figures, 4 tables

MatrAIx: Simulating the World with 8.3 Billion Persona Agents

Authors: Xiaomin Li, Yuexing Hao, Jianheng Hou, Jintao Huang, Qianfeng Wen, Shirley Huang, Yifan Liu, Xiaoyi Liu, Yilan Fan, Yijun Wang, Koutian Wu, Ruoqi Gao, Muhammad Ahmed Mohsin, Jing Tang, Brihi Joshi, Heming Liu, Zheyuan Deng, Zonglin Di, Sankalp Jajee, Jiuyao Lu, Zhiwei Zhang, Saksham Kapoor, Ishan Gupta, Yunhan Zhao, Chanwoo Park , et al. (68 additional authors not shown)

Abstract: Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First,… ▽ More Human evaluation of AI systems and digital products is costly, slow, and difficult to scale. Offline evaluations are more scalable but often abstract away human diversity and interactive behavior. We therefore introduce MatrAIx, a population-scale simulated-user evaluation infrastructure for testing AI systems and digital products with heterogeneous users. MatrAIx has three core components: First, Persona 8B contains 8.3 billion persona records represented by 1,290 categorical dimensions. Records are either sampled from a dependency graph that preserves correlated attributes or derived from human-authored profiles. We release a quality-filtered coreset of approximately 1 million personas, comprising 599,847 human-grounded and 400,000 synthetic records. Second, the MatrAIx Playground provides four environments in which diverse users evaluate and interact with digital products: Survey, AI Chatbot, Web, and App. Third, MatrAIx provides 1,010 application tasks spanning more than 25 domains, including Commerce, Software, Finance, and Healthcare. We conducted 18,189 evaluation trials across eight representative tasks. Persona agents were powered by three LLMs: Claude Opus 4.8, GPT 5.5, and Claude Haiku 4.5. The resulting feedback captures how decisions and preferences vary across persona backgrounds, including hesitation after a price increase, willingness to continue after an AI assistant fails, and latency tolerance. We conducted two main validation studies: First, a 400-trial controlled study evaluated persona adherence across ten behavioral attributes and all four environments. The declared behavior was expressed or correctly suppressed in 366 trials (91.5%). Second, human and LLM judges evaluated the extraction quality of human-grounded personas. Overall, MatrAIx provides an end-to-end infrastructure for evaluating AI systems and digital products with diverse simulated human users. △ Less

Submitted 4 August, 2026; originally announced August 2026.

Comments: Project website: https://matraix.ai

FilmBench: A Film-Grade Benchmark for Cinematic Video Generation

Authors: Shengyi Wang, Niantong Li, Guangzheng Hu, Hong Qi, Fei Ding, Weixu Qiao, Jinlin Wang, Xiaotong Lv, Peng Han, Zimeng Li, Fanshu Ding, Yushu Wang, Han Wu, Jingjing Chen, Chongxiao Wang, Yanhao Wu, Chenglong Huang, Xiaoqian Zhu, Jie Tian, Hua Li, Jingjing Fan, Mingshuang Tang, Zhong Li, Hengxia Qiang, Weibin Chen , et al. (5 additional authors not shown)

Abstract: Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models. More fundamentally, their evaluation taxonomies remain rudimentary (overall visual quality, coarse text alignment and temporal smoothness) rather than… ▽ More Progress in video generation keeps narrowing the visual gap between AI-generated and professionally produced footage, yet most benchmarks still draw prompts from web sources or LLM templates and score them with untrained, generic multimodal models. More fundamentally, their evaluation taxonomies remain rudimentary (overall visual quality, coarse text alignment and temporal smoothness) rather than the professional Cinematic Language criteria by which films are actually made and judged, so they assess basic video plausibility rather than film-grade craft. We introduce FilmBench, a text-to-video (T2V) and reference-to-video (R2V) benchmark grounded in the professional Cinematic Language of the film- academy tradition and co-developed with directors and faculty from the Beijing Film Academy and the Hujing Digital Media & Entertainment Group film studio. It rests on three choices. First, prompts are reverse-engineered from clips of award-winning films spanning 20 cinematic genres and chosen by professional directors, so every prompt is anchored to a verified live-action reference; the prompts follow real shot lists, and most script multiple shots (1,056 of the 1,169 prompts are multi-shot), unlike prior single-clip benchmarks. Second, evaluation follows a three-level Cinematic taxonomy of 3 axes, 12 components and 35 (T2V) +3 (R2V-only) sub-metrics. Third, we develop an in-house expert-grade automatic evaluation agent and open-source its core suite of Cinematic Language operators (FilmOps). Benchmarking leading video generation models (9 for T2V, 7 for R2V), the evaluator reproduces the human model ranking at model-level Spearman \r{ho} = 0.95 (T2V) and 0.96 (R2V). Scores fall well below prior web-style benchmarks, with two consistent gaps in dynamic aesthetics and a marked single- to multi-shot performance drop that widens for weaker models. △ Less

Submitted 29 July, 2026; v1 submitted 27 July, 2026; originally announced July 2026.

The Extended Ultrahigh-energy Gamma-Ray Emission in the Vicinity of PSR J2238+5903

Authors: Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao, D. Bastieri, X. J. Bi, Y. J. Bi, W. Bian, J. Blunier, A. V. Bukevich, C. M. Cai, W. Y. Cao, Zhe Cao, J. Chang, J. F. Chang, E. S. Chen, G. H. Chen, H. K. Chen, L. F. Chen, Liang Chen, Long Chen, M. J. Chen, M. L. Chen, Q. H. Chen, S. Chen , et al. (305 additional authors not shown)

Abstract: We present a comprehensive analysis of the recently discovered TeV gamma-ray source, LHAASO J2238+5900. Based on data collected from the LHAASO, our fitting results suggest that the source is significantly extended with an angular extension of 0.54° \pm 0.01° and is spatially coincident with the pulsar PSR J2238+5903. Its spectrum is characterized by a power-law with a cutoff at 41.0\pm 3.5 TeV. A… ▽ More We present a comprehensive analysis of the recently discovered TeV gamma-ray source, LHAASO J2238+5900. Based on data collected from the LHAASO, our fitting results suggest that the source is significantly extended with an angular extension of 0.54° \pm 0.01° and is spatially coincident with the pulsar PSR J2238+5903. Its spectrum is characterized by a power-law with a cutoff at 41.0\pm 3.5 TeV. Additionally, the source exhibits a significant signal of 7.9σabove 100 TeV, implying that it is a PeVatron candidate. While the gamma-ray emission is consistent with a pulsar wind nebula (PWN) scenario, the relatively large extension size also allows for a halo interpretation, potentially caused by electron-positron pairs escaping from the PWN. △ Less

Submitted 23 July, 2026; originally announced July 2026.

Quantum Sensing Beyond Exceptional Points via Hidden symmetry-protected vacuum-noise fixed point

Authors: Wencong Wang, Yuyang Liang, Peng Han, Xianqiu Wu, Dongmei Liu, Min Gu

Abstract: Exceptional-point (EP) sensing has attracted considerable interest because of its anomalous response scaling. However, recent studies have shown that the enhanced response near an EP is inevitably accompanied by amplified quantum noise, fundamentally limiting the achievable signalto-noise ratio (SNR). Here, we propose a fundamentally different route toward non-Hermitian quantum sensing based on sy… ▽ More Exceptional-point (EP) sensing has attracted considerable interest because of its anomalous response scaling. However, recent studies have shown that the enhanced response near an EP is inevitably accompanied by amplified quantum noise, fundamentally limiting the achievable signalto-noise ratio (SNR). Here, we propose a fundamentally different route toward non-Hermitian quantum sensing based on symmetry-protected noise suppression rather than response amplification. We develop a fully quantum continuous-variable model that unifies parity-time (PT) and anti-paritytime(APT) symmetries within a single framework. Exploiting the incompatibility between these two symmetries, we uncover a non-Hermitian Dirac eigenspectrum and reveal a hidden symmetryprotected phase transition embedded in the Hamiltonian spectrum. Remarkably, this hidden phasetransition simultaneously constitutes a symmetry-protected vacuum-noise fixed point, where collective three-mode quadratures exhibit suppressed quantum fluctuations despite the absence of any anomalous spectral response. As a consequence, quantum sensing is enhanced through the suppression of excess quantum noise while maintaining a finite response sensitivity, establishing a sensing mechanism fundamentally different from conventional EP-based approaches. These results reveal an unexpected connection between hidden symmetry, quantum fluctuations, and non-Hermitian quantum metrology, and establish noise suppression as an alternative paradigm for non-Hermitian quantum sensing. △ Less

Submitted 21 July, 2026; originally announced July 2026.

Open Models, Open Risks: Measuring Unsafe Generation in Text-to-Image Models In the Wild

Authors: Peilin Han, Yang Liu, Yilong Yang, Jingchun Zhang, Teng Li, Jianfeng Ma, Zhuo Ma

Abstract: Existing safety studies on text-to-image (T2I) jailbreaks are largely conducted in controlled in-the-lab settings, typically on a small number of canonical models. As a result, the current safety status of the rapidly growing in-the-wild T2I ecosystem remains unclear. This uncertainty is amplified by two factors: existing detector-based metrics are designed for controlled evaluation, and in-the-wi… ▽ More Existing safety studies on text-to-image (T2I) jailbreaks are largely conducted in controlled in-the-lab settings, typically on a small number of canonical models. As a result, the current safety status of the rapidly growing in-the-wild T2I ecosystem remains unclear. This uncertainty is amplified by two factors: existing detector-based metrics are designed for controlled evaluation, and in-the-wild risks may arise not only from adversarial prompting, but also from unsafe release practices and unsafe model derivatives. In this paper, we present a large-scale empirical study of in-the-wild T2I safety through the lens of jailbreak. We first show that detector-only jailbreak metrics substantially overestimate practical risk over in the wild due to semantic drift and generation artifacts, and we introduce Advanced ASR to better capture semantically valid and visually plausible unsafe generation. Using this refined metric, we evaluate 200+ in-the-wild T2I models from Hugging Face under three representative jailbreak attacks. Our results show that many downstream models retain a non-trivial degree of safety even without explicit post-hoc safeguards, indicating that safety degradation in the wild is neither universal nor uniform. At the same time, we identify a set of high-risk models, including explicitly NSFW-oriented releases as well as seemingly benign models whose unsafe behavior is only exposed through systematic evaluation. We further trace these models to their release context and report high-risk cases to Hugging Face. △ Less

Submitted 8 July, 2026; originally announced July 2026.

SocialPersona: Benchmarking Personalized Profiling and Response with Multimodal Social-Media Context

Authors: Qinkai Zhang, Yanyan Zhao, Xin Lu, Yulin Hu, Pengtao Han, Bing Qin

Abstract: Personalized language-model assistants are often evaluated through a memory lens: can a model recall preferences users have explicitly stated in dialogue? More comprehensive personalization demands a harder capability -- inferring what users care about from the multimodal traces they naturally leave behind. We introduce SocialPersona, a benchmark for evaluating whether multimodal large language mo… ▽ More Personalized language-model assistants are often evaluated through a memory lens: can a model recall preferences users have explicitly stated in dialogue? More comprehensive personalization demands a harder capability -- inferring what users care about from the multimodal traces they naturally leave behind. We introduce SocialPersona, a benchmark for evaluating whether multimodal large language models (MLLMs) can recover revealed preferences from longitudinal social-media timelines and use them in dialogue. Built from longitudinal timelines of 171 everyday, non-promotional social-media users, SocialPersona contains text, images, timestamps, and 2,597 human-verified preference tags across seven interest domains, separating stable interests from recent interests. It supports two tasks: constructing structured user profiles from multimodal context and generating responses aligned with inferred profiles. Experiments with proprietary and open-weight MLLMs show that models can identify broad interest domains, yet their performance drops on fine-grained and recent interests and degrades further when inferred profiles must be used to personalize dialogue. Together with evidence that text and images provide complementary preference signals, these results indicate that robust cross-modal, long-horizon user modeling remains a key challenge, and that SocialPersona can help measure and advance progress toward assistants that infer and act on revealed preferences. △ Less

Submitted 25 June, 2026; originally announced June 2026.

Extreme PeV accelerator associated with GRS 1915+105

Authors: Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao, D. Bastieri, X. J. Bi, Y. J. Bi, W. Bian, J. Blunier, A. V. Bukevich, C. M. Cai, Y. Y. Cai, W. Y. Cao, Zhe Cao, J. Chang, J. F. Chang, E. S. Chen, G. H. Chen, H. K. Chen, L. F. Chen, Liang Chen, Long Chen, M. J. Chen, M. L. Chen, Q. H. Chen , et al. (304 additional authors not shown)

Abstract: Microquasars, binary systems featuring relativistic jets, have emerged as sources for particle acceleration beyond PeV energies. We present a study of the broadband $γ$-ray emission from one of the most prominent Galactic microquasars GRS 1915+105 based on data accumulated by LHAASO and Fermi-LAT over 4 and 17 years, respectively. A joint analysis of LHAASO-WCDA and LHAASO-KM2A data reveals extend… ▽ More Microquasars, binary systems featuring relativistic jets, have emerged as sources for particle acceleration beyond PeV energies. We present a study of the broadband $γ$-ray emission from one of the most prominent Galactic microquasars GRS 1915+105 based on data accumulated by LHAASO and Fermi-LAT over 4 and 17 years, respectively. A joint analysis of LHAASO-WCDA and LHAASO-KM2A data reveals extended $γ$-ray emission whose centroid appears significantly shifted, by ~ 0.13°, from the binary system and its jets. The spectral energy distribution is well described by a curved spectrum with progressive steepening that can be described by a log-parabola function with no evidence for a sharp cutoff, consistent with parent particles reaching multi-PeV energies and an extreme acceleration efficiency approaching the limit set by the available potential drop across the source. Several features, most notably the shift of the emission and single-power-law spectrum down to GeV band, favor radiation by cosmic rays accelerated in the source interacting with the dense ambient medium. Our spectral modeling implies that at least a few percent of the jet mechanical power is transferred to protons, whose maximum energy reaches beyond 5 PeV. These results strengthen the case for microquasars as exceptionally efficient accelerators in our Galaxy. △ Less

Submitted 25 June, 2026; v1 submitted 23 June, 2026; originally announced June 2026.

Comments: 10 pages, 4 figures, with supplementary material. Corrected a typo in the y-axis units of Fig. 2

Agentic Electronic Design Automation: A Handoff Perspective

Authors: Jiawei Liu, Peiyi Han, Yuntao Lu, Su Zheng, Fengyu Yan, Bei Yu

Abstract: Electronic design automation (EDA) is inherently multi-stage and handoff-heavy. Design artifacts, flow scripts, and engineering decisions cross tool, session, and organizational boundaries before final implementation, signoff, or release. Each transfer carries explicit and implicit requirements that may not be fully captured by stage-local checks. LLM-based agents now invoke EDA tools directly, em… ▽ More Electronic design automation (EDA) is inherently multi-stage and handoff-heavy. Design artifacts, flow scripts, and engineering decisions cross tool, session, and organizational boundaries before final implementation, signoff, or release. Each transfer carries explicit and implicit requirements that may not be fully captured by stage-local checks. LLM-based agents now invoke EDA tools directly, embed retrieved knowledge in executable scripts, and hand off state across sessions and stages. Once their outputs condition downstream engineering decisions, the transferred object must satisfy a handoff contract and meet the assumptions of its next consumer. This survey introduces handoff validity as its organizing principle. A handoff is valid when the transferred object satisfies the consumer's acceptance conditions and carries sufficient context, evidence, and provenance for downstream use. We review 82 systems and classify them into three boundary classes. Stage-Bound systems establish validity within a single EDA stage or bounded verification task. Flow-Bound systems preserve coherent workflow state across tools, invocations, and sessions. Organization-Bound systems maintain source grounding, provenance, scope, and admissibility across knowledge and authority boundaries. For each class, we analyze handoff contracts, handoff objects, coordination mechanisms, and open questions. These analyses motivate a five-layer EDA agent communication protocol (EACP), covering the agent discovery, agent message, tool invocation, workflow orchestration, and security and IP protocols. We aim to provide a common vocabulary and research agenda for trustworthy agentic EDA. △ Less

Submitted 18 June, 2026; originally announced June 2026.

Label Shift Aware Adaptation for Online Zero-shot Learning with Contrastive Language-Image Pre-Training (CLIP)

Authors: Pengxiao Han, Changkun Ye, Yanshuo Wang, Jinguang Tong, Miaohua Zhang, Xuesong Li, Jie Hong, Lars Petersson

Abstract: Vision-language models like Contrastive Language-Image Pre-Training (CLIP) have been extensively studied in data-scarce scenarios. A particularly challenging and realistic task in this area is online zero-shot learning with CLIP, where unknown test samples are predicted sequentially in random order by CLIP while keeping the feature extraction and model parameters fixed during the sequential infere… ▽ More Vision-language models like Contrastive Language-Image Pre-Training (CLIP) have been extensively studied in data-scarce scenarios. A particularly challenging and realistic task in this area is online zero-shot learning with CLIP, where unknown test samples are predicted sequentially in random order by CLIP while keeping the feature extraction and model parameters fixed during the sequential inference phase. Most existing approaches in this setting address the problem by adapting representations online using incoming test samples, while neglecting the distribution of the data on which CLIP was initially trained. This mismatch can lead to degraded performance when the label distribution in the test data differs from that of the training domain. To address this gap, we propose Label Shift Aware (LSA), which formulates the online zero-shot classification task as a domain adaptation problem. Specifically, LSA adapts the predictions computed by CLIP, which was trained on an unknown source distribution, to a target distribution using only unlabeled test data, and applies label shift correction to mitigate the mismatch between the source and target domains. The extensive experiments across multiple datasets demonstrate that the proposed LSA consistently outperforms state-of-the-art online zero-shot learning methods based on CLIP. △ Less

Submitted 13 June, 2026; originally announced June 2026.

Rethinking Psychometric Evaluation of LLMs: When and Why Self-Reports Predict Behavior

Authors: Rafal Kocielnik, Pengrui Han, Peiyang Song, Myrl G. Marmarelis, Ramit Debnath, Dean Mobbs, Anima Anandkumar, R. Michael Alvarez

Abstract: Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work documented substantial SR-behavior dissociation in LLMs, but relied on broad personality traits (Big 5) that predict specific behaviors weakly, even in humans. Furthermore, the isolation of conversational sessions combined wi… ▽ More Anticipating LLM behavioral tendencies from low-cost psychometric probes is critical for safe deployment, but only if self-reports (SR) reliably predict behavior. Recent work documented substantial SR-behavior dissociation in LLMs, but relied on broad personality traits (Big 5) that predict specific behaviors weakly, even in humans. Furthermore, the isolation of conversational sessions combined with weak context matching left open whether LLMs truly lack coherence or whether the conditions needed to detect such coherence were not met. We contrast Big 5 with the Theory of Planned Behavior (TPB), which measures intention targeted to a specific behavior and predicts human behavior substantially better than broad traits. We run experiments across four behavioral tasks and 11 frontier LLMs, while also varying session context and identity induction. We find that SR-behavior coherence exists but is selective. 1) Within a shared conversation, the Theory of Planned Behavior reaches human-level coherence; Big 5 does not. 2) Across separate conversations, coherence survives only for behaviors anchored outside the immediate prompt, such as implicit bias shaped by training, and collapses when behavior is strongly primed by context, as with sycophancy. 3) Persona prompting makes self-reports more consistent across conversations, but does not bring behavior into alignment. These findings suggest that coarse personality frameworks, such as Big 5 may not be the best tools for testing deployment behavior. More task- and behavior-specific instruments are needed, and even these must be evaluated across tasks and contexts. △ Less

Submitted 10 June, 2026; originally announced June 2026.

Comments: Accepted as an Oral (Contributed Talk) at the ICML 2026 Workshop on Combining Theory and Benchmarks (CTB)

MSC Class: 68T50 ACM Class: I.2.7; I.2.6; K.4.0

FACTR 2: Learning External Force Sensing for Commodity Robot Arms Improves Policy Learning

Authors: Steven Oh, Jason Jingzhou Liu, Tony Tao, Philip Han, Kenneth Shaw, Satoshi Funabashi, Ruslan Salakhutdinov, Deepak Pathak

Abstract: Contact-rich manipulation requires force sensitivity, but many robot arms lack dedicated force sensors due to their high cost. We present Neural External Torque Estimation (NEXT), a data-driven method that estimates external joint torques without needing any dedicated force sensors. NEXT trains in 1 minute from only 10 minutes of free-motion data, yet achieves estimates comparable to dedicated joi… ▽ More Contact-rich manipulation requires force sensitivity, but many robot arms lack dedicated force sensors due to their high cost. We present Neural External Torque Estimation (NEXT), a data-driven method that estimates external joint torques without needing any dedicated force sensors. NEXT trains in 1 minute from only 10 minutes of free-motion data, yet achieves estimates comparable to dedicated joint-torque sensors. NEXT enables force-feedback teleoperation on low-cost arms and improves policy learning through Force-Informed Re-Sampling Training (FIRST), which up-samples pre-contact and contact segments during behavior cloning. Across five long-horizon tasks, FIRST outperforms prior force-aware policies by over 17% in task progress. Together, NEXT and FIRST bring force-aware teleoperation and policy learning to off-the-shelf robots without additional sensing hardware. Video results and code are available at https://jasonjzliu.com/factr2 △ Less

Submitted 12 August, 2026; v1 submitted 10 June, 2026; originally announced June 2026.

Comments: Website at https://jasonjzliu.com/factr2

$Ψ$-Bench: Evaluating Persona-Sensitive Influencing in Persuasive Dialogues

Authors: Peixuan Han, Hongyi Du, Jiayu Liu, Yihang Sun, Yutong Liu, Jiaxuan You

Abstract: Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responders to user preferences, limiting their ability to interact with users and provide suggestions or guidance proactively. To systematically evaluate such proactive personalization in realistic interactions, we propose $Ψ$-Bench, a benchmark for assess… ▽ More Personalization is a crucial capability of modern language agents. However, current research primarily positions personalized agents as passive responders to user preferences, limiting their ability to interact with users and provide suggestions or guidance proactively. To systematically evaluate such proactive personalization in realistic interactions, we propose $Ψ$-Bench, a benchmark for assessing LLMs' ability to influence realistic users through conversation. We design three real-world interaction scenarios that involve persuasion in $Ψ$-Bench, and endow simulated clients with personal characteristics through explicit user profiles derived from dialogue histories. We evaluate 10 frontier LLMs on $Ψ$-Bench and find that while most models can produce coherent and reasonable arguments, even state-of-the-art models still leave considerable room for improvement in persuasion. We also find that providing access to client profiles yields an average performance gain of 18.24\%, highlighting the importance of user-specific information for effective persuasion. Overall, our work highlights persona-sensitive influencing as a challenging yet practical direction for evaluating and developing more proactive personalized LLM agents. Codes are available at: https://github.com/Hanpx20/Psi-Bench. △ Less

Submitted 1 June, 2026; originally announced June 2026.

RAG4Outcome: A Retrieval-Augmented Multimodal Framework for Prognostic Prediction in Chronic Osteomyelitis

Authors: Daqian Shi, Pei Han, Jishizhan Chen, Yang Wang, Xiaolei Diao, Xianyou Zheng, Pengfei Cheng

Abstract: Chronic osteomyelitis presents substantial prognostic challenges due to its high recurrence risk and complex postoperative recovery trajectories. Traditional assessment often relies on manual scoring systems, which limit scalability, efficiency, and consistency in clinical practice. Furthermore, the heterogeneous nature of clinical data poses challenges for current multimodal learning approaches t… ▽ More Chronic osteomyelitis presents substantial prognostic challenges due to its high recurrence risk and complex postoperative recovery trajectories. Traditional assessment often relies on manual scoring systems, which limit scalability, efficiency, and consistency in clinical practice. Furthermore, the heterogeneous nature of clinical data poses challenges for current multimodal learning approaches that require aligned inputs and large annotated datasets. In this work, we propose RAG4Outcome, a retrieval-augmented generation (RAG) framework for prognostic prediction in chronic osteomyelitis. Our method integrates multimodal clinical data, including PET-CT imaging reports, structured surgical and diagnostic records, and unstructured follow-up notes, into a unified prediction pipeline. By combining a domain-specific retrieval corpus with expert-guided prompting, the framework enables more interpretable, evidence-grounded, and clinically reliable prognosis. Preliminary results on real-world cases demonstrate promising effectiveness and clinical alignment, highlighting the potential of RAG4Outcome for AI-assisted infection management and postoperative decision support. △ Less

Submitted 24 April, 2026; originally announced May 2026.

Replay-guided Test-time Adaptation for Fault Diagnosis Under Unseen Operating Conditions

Authors: Yakun Wang, Pengyu Han, Zeyi Liu, Xiao He, Dongming Cai, Hongshuo Zhao

Abstract: In modern industrial systems, machinery frequently operates under dynamic environments with continuously varying loads and speeds. Consequently, deep learning-based fault diagnosis models often suffer from severe performance degradation under unseen operating conditions due to complex data distribution shifts. Since existing methods predominantly rely on static offline training, they lack the capa… ▽ More In modern industrial systems, machinery frequently operates under dynamic environments with continuously varying loads and speeds. Consequently, deep learning-based fault diagnosis models often suffer from severe performance degradation under unseen operating conditions due to complex data distribution shifts. Since existing methods predominantly rely on static offline training, they lack the capability to dynamically adapt to these continuous variations. To address this issue, an integrated framework combining offline domain generalization (DG) and online test-time adaptation (OTTA) is proposed. Initially, a model with preliminary generalization capability is obtained offline by extracting domain-invariant features via adversarial learning. During the online phase, a dual-memory replay mechanism is developed. By selectively storing high-confidence online pseudo-labeled samples and replaying them with historical offline data, the model facilitates adaptation to changing data distributions and helps reduce forgetting of previously learned knowledge Experiments on a real-world motor dataset show that the proposed approach achieves competitive performance under the considered unseen operating conditions. △ Less

Submitted 21 May, 2026; originally announced May 2026.

Comments: 6 pages, 2 figures

Interactive Evaluation Requires a Design Science

Authors: Keyang Xuan, Peiyang Song, Pan Lu, Pengrui Han, Wenkai Li, Zhenyu Zhang, Zexue He, Wenyue Hua, Manling Li, Jiaxuan You, Adrian Weller, Yizhong Wang, Jiaxin Pei

Abstract: AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents, while many evaluation practices still inherit assumptions from response-centered benchmarks (e.g., fixed inputs, isolated outputs, and outcome judgments that can be made from a single response). The field has beg… ▽ More AI evaluation is undergoing a structural change. Large language models (LLMs) are increasingly deployed as systems that act over time through tools, environments, users, and other agents, while many evaluation practices still inherit assumptions from response-centered benchmarks (e.g., fixed inputs, isolated outputs, and outcome judgments that can be made from a single response). The field has begun to build interactive benchmarks, but the resulting landscape is fragmented: benchmarks differ in what interaction artifacts they admit, how trajectories are scored, and what claims their results support. This position paper argues that interactive evaluation should be treated as a principled evaluation paradigm, not merely a new family of agent benchmarks. Simply adopting previous evaluation paradigms does not suffice. We define evaluation as an autonomous mapping from evidence to judgments, and show that interactive evaluation changes both sides of this mapping: the evidence becomes interaction-generated trajectories, while the evaluation procedure must assess process, recoverability, coordination, robustness, and system-level performance. Building on this definition, we propose a two-axis taxonomy, derive design principles and reporting standards, examine representative scenarios, and analyze how longstanding evaluation challenges reappear at the trajectory level. △ Less

Submitted 18 May, 2026; originally announced May 2026.

Comments: 10 pages

Tracing the Arrow of Time: Diagnosing Temporal Information Flow in Video-LLMs

Authors: Peitao Han, Fei Cheng, Lis K. Pereira, Qianying Liu, Shigeru Kitazawa

Abstract: The Arrow-of-Time (AoT) task, determining whether a video plays forward or backward by recognizing temporal irreversibility, is one humans solve with near-perfect accuracy, yet frontier Video Large Language Models (Video-LLMs) perform only modestly above chance. This gap raises a key question: do visual backbones fail to encode temporal information, or does information bottleneck lie elsewhere in… ▽ More The Arrow-of-Time (AoT) task, determining whether a video plays forward or backward by recognizing temporal irreversibility, is one humans solve with near-perfect accuracy, yet frontier Video Large Language Models (Video-LLMs) perform only modestly above chance. This gap raises a key question: do visual backbones fail to encode temporal information, or does information bottleneck lie elsewhere in the Video-LLM architecture? We address this question by isolating the vision encoder from the Video-LLM and tracing temporal information across the encoder, projector, and LLM. We find that video-centric encoders with explicit temporal modeling encode strong temporal signals, whereas frame-centric encoders do not. However, when video-centric representations are passed through a standard Video-LLM architecture, performance often collapses, revealing a bottleneck of temporal information flow. We identify projector design as a key factor: Q-Former disrupts temporal information, while a time-preserved MLP projection substantially improves the LLM's access to such information. Our layer-wise analysis further shows temporal representation dynamics across encoder layers. Guided by these findings, we build a Video-LLM with temporal-aware video-centric encoder, time-preserved projector, and AoT supervision, surpassing human performance on AoT$_{PPB}$ with 98.1\% accuracy, and improving broader temporal reasoning tasks by up to 6.0 points on VITATECS-Direction and 1.3 points on TVBench. Our results show that temporal reasoning in Video-LLMs requires both effective temporal encoding and reliable transfer of this information to the LLM. △ Less

Submitted 8 May, 2026; originally announced May 2026.

Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning

Authors: Yiming Huang, Zhenbo Shi, Shuzheng Gao, Cuiyun Gao, Peiyi Han, Chuanyi Liu

Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically rely on static policy optimization schemes that misalign with the model's evolving reasoning capabilities. To address this issue, we propose Adaptive Power-Mean Policy Optimization (APMPO), which comprises two m… ▽ More Reinforcement Learning with Verifiable Rewards (RLVR) is an essential paradigm that enhances the reasoning capabilities of Large Language Models (LLMs). However, existing methods typically rely on static policy optimization schemes that misalign with the model's evolving reasoning capabilities. To address this issue, we propose Adaptive Power-Mean Policy Optimization (APMPO), which comprises two main innovations: Power-Mean Policy Optimization (PMPO) and Feedback-Adaptive Clipping (FAC). Specifically, PMPO introduces a generalized power-mean objective. This enables the model to adaptively transition from the signal-amplifying behavior of the arithmetic mean to the consistency-enforcing behavior of the geometric mean. FAC adaptively adjusts clipping bounds based on real-time reward statistics to overcome the limitations of static mechanisms. Capitalizing on these innovations, APMPO improves learning dynamics and reasoning performance. Extensive experiments on nine datasets across three reasoning tasks showcase the superiority of APMPO over state-of-the-art RLVR-based baselines. For instance, APMPO boosts the average Pass@1 score on mathematical reasoning benchmarks by 3.0 points compared to GRPO when using Qwen2.5-3B-Instruct. △ Less

Submitted 7 May, 2026; v1 submitted 11 April, 2026; originally announced May 2026.

Comments: Accepted to ACL 2026 (Findings)

Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs

Authors: Yiming Huang, Zhenbo Shi, Xin-Cheng Wen, Jichuan Zeng, Cuiyun Gao, Peiyi Han, Chuanyi Liu

Abstract: Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based methods often lack the capacity to adapt to the model's evolving reasoning capabilities during training. Therefore, these methods can misdirect policy optimization in the absence of ground-truth supervision. To address t… ▽ More Unsupervised reinforcement learning (RL) has emerged as a promising paradigm for enabling self-improvement in large language models (LLMs). However, existing unsupervised RL-based methods often lack the capacity to adapt to the model's evolving reasoning capabilities during training. Therefore, these methods can misdirect policy optimization in the absence of ground-truth supervision. To address this issue, we introduce FREIA, a novel RL-based algorithm built on two key innovations: (1) Free Energy-Driven Reward (FER) adapts rewards to balance consensus and exploration based on the Free Energy Principle. (2) Adaptive Advantage Shaping (AAS) adaptively adjusts learning signals based on the statistical characteristics of sampled rewards. Empirical evaluations on nine datasets across three reasoning tasks showcase that FREIA outperforms other unsupervised RL-based baselines. Notably, in mathematical reasoning tasks, FREIA surpasses other methods by an average of 0.5 to 3.5 points in Pass@1 using the DeepSeek-R1-Distill-Qwen-1.5B model. △ Less

Submitted 7 May, 2026; v1 submitted 11 April, 2026; originally announced May 2026.

Comments: Accepted by ACL 2026

Resolving spurious topological entanglement entropy in stabilizer codes

Authors: Peilun Han, Zijian Liang, Yifei Wang, Bowen Yang, Yingfei Gu, Yu-An Chen

Abstract: Topological entanglement entropy (TEE) is a key diagnostic of long-range entanglement in two-dimensional gapped phases of matter, but it can suffer from spurious contributions that overestimate the total quantum dimension of the underlying topological order. In this work, we identify the microscopic origin of spurious TEE and introduce a concave partition for computing the Levin-Wen TEE of transla… ▽ More Topological entanglement entropy (TEE) is a key diagnostic of long-range entanglement in two-dimensional gapped phases of matter, but it can suffer from spurious contributions that overestimate the total quantum dimension of the underlying topological order. In this work, we identify the microscopic origin of spurious TEE and introduce a concave partition for computing the Levin-Wen TEE of translation-invariant stabilizer codes of prime-dimensional qudits. We rigorously prove that this prescription is free of spurious contributions. As a complementary probe, we study bivariate bicycle codes on a bipartite cylinder and show that the entanglement entropy depends sensitively on the cylinder circumference, revealing topological frustration of the underlying anyons. △ Less

Submitted 29 April, 2026; originally announced April 2026.

Comments: 7+46 pages, 15 figures, 1 table

GraphPlanner: Graph Memory-Augmented Agentic Routing for Multi-Agent LLMs

Authors: Tao Feng, Haozhen Zhang, Zijie Lei, Peixuan Han, Jiaxuan You

Abstract: LLM routing has achieved promising results in integrating the strengths of diverse models while balancing efficiency and performance. However, to support more realistic and challenging applications, routing must extend into agentic LLM settings, where task planning, multi-round cooperation among heterogeneous agents, and memory utilization are indispensable. To address this gap, we propose GraphPl… ▽ More LLM routing has achieved promising results in integrating the strengths of diverse models while balancing efficiency and performance. However, to support more realistic and challenging applications, routing must extend into agentic LLM settings, where task planning, multi-round cooperation among heterogeneous agents, and memory utilization are indispensable. To address this gap, we propose GraphPlanner, a heterogeneous graph memory-augmented agentic router for multi-agent LLMs that generates routing workflows for each query and supports both inductive and transductive inference. GraphPlanner formulates workflow generation as a Markov Decision Process (MDP), where at each step it selects both the LLM backbone and the agent role, including Planner, Executor, and Summarizer. By leveraging a heterogeneous graph, denoted as GARNet, to capture interaction memories among queries, agents, and responses, GraphPlanner integrates historical memory and workflow memory into richer state representations. The entire pipeline is optimized with reinforcement learning, jointly improving task-specific performance and computational efficiency. We evaluate GraphPlanner across 14 diverse LLM tasks and demonstrate that: (1) GraphPlanner outperforms strong single-round and multi-round routers, improving accuracy by up to 9.3% while reducing GPU cost from 186.26 GiB to 1.04 GiB; (2) GraphPlanner generalizes robustly to unseen tasks and LLMs, exhibiting strong zero-shot capabilities; and (3) GraphPlanner effectively leverages historical memories, supporting both inductive and transductive inference for more adaptive routing. Our code for GraphPlanner is released at https://github.com/ulab-uiuc/GraphPlanner. △ Less

Submitted 26 April, 2026; originally announced April 2026.

Journal ref: ICLR 2026

Ultra-high-energy $γ$-ray imprints from PeV particles accelerated by supernova remnants

Authors: Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao, D. Bastieri, X. J. Bi, Y. J. Bi, W. Bian, J. Blunier, A. V. Bukevich, C. M. Cai, Y. Y. Cai, W. Y. Cao, Zhe Cao, J. Chang, J. F. Chang, E. S. Chen, G. H. Chen, H. K. Chen, L. F. Chen, Liang Chen, Long Chen, M. J. Chen, M. L. Chen, Q. H. Chen , et al. (303 additional authors not shown)

Abstract: The quest for the origin of cosmic ray (CRs) is a fundamental issue in astrophysics. Shocks of supernova remnants (SNRs) have been considered as the dominant contributors to Galactic CRs below the spectral knee near $\sim 3$ petaelectronvolt (PeV). Whether SNRs are efficient accelerators of particles beyond PeV energies has long been debated. Here we report observations of very-high-energy $γ$-ray… ▽ More The quest for the origin of cosmic ray (CRs) is a fundamental issue in astrophysics. Shocks of supernova remnants (SNRs) have been considered as the dominant contributors to Galactic CRs below the spectral knee near $\sim 3$ petaelectronvolt (PeV). Whether SNRs are efficient accelerators of particles beyond PeV energies has long been debated. Here we report observations of very-high-energy $γ$-ray emission up to hundreds of TeV from two middle age shell-type SNRs, G150.3$+$4.5 and $γ$-Cygni, with the Large High Altitude Air Shower Observatory (LHAASO). Two (or three) distinct morphological/spectral components with convex spectral shapes are observed in both sources, with the low-energy one being more extended than the high-energy one. %Although it is possible that these high-energy components may be driven by powerful pulsars, The likely association of the high-energy component with molecular clouds at similar distances, and the weakness/absence of pulsar wind nebulae (PWNe) inside these SNRs clearly indicate for the first time that the highest energy emission is produced by collision of hadronic CRs up to PeV energies with the clouds. These results are compatible with the classic model prediction that PeV particles accelerated near the end of the free expansion phase of SNR evolution can illuminate nearby molecular clouds (MCs) to produce strong $γ$-ray emission. △ Less

Submitted 24 April, 2026; originally announced April 2026.

Comments: 31 pages, 8 figures, 3 Tables

ONOTE: Benchmarking Omnimodal Notation Processing for Expert-level Music Intelligence

Authors: Menghe Ma, Siqing Wei, Yuecheng Xing, Yaheng Wang, Fanhong Meng, Peijun Han, Luu Anh Tuan, Haoran Luo

Abstract: Omnimodal Notation Processing (ONP) represents a unique frontier for omnimodal AI due to the rigorous, multi-dimensional alignment required across auditory, visual, and symbolic domains. Current research remains fragmented, focusing on isolated transcription tasks that fail to bridge the gap between superficial pattern recognition and the underlying musical logic. This landscape is further complic… ▽ More Omnimodal Notation Processing (ONP) represents a unique frontier for omnimodal AI due to the rigorous, multi-dimensional alignment required across auditory, visual, and symbolic domains. Current research remains fragmented, focusing on isolated transcription tasks that fail to bridge the gap between superficial pattern recognition and the underlying musical logic. This landscape is further complicated by severe notation biases toward Western staff and the inherent unreliability of "LLM-as-a-judge" metrics, which often mask structural reasoning failures with systemic hallucinations. To establish a more rigorous standard, we introduce ONOTE, a multi-format benchmark that utilizes a deterministic pipeline--grounded in canonical pitch projection--to eliminate subjective scoring biases across diverse notation systems. Our evaluation of leading omnimodal models exposes a fundamental disconnect between perceptual accuracy and music-theoretic comprehension, providing a necessary framework for diagnosing reasoning vulnerabilities in complex, rule-constrained domains. △ Less

Submitted 22 April, 2026; originally announced April 2026.

Comments: 12 pages, 8 figures

Controllable non-Hermitian topology in a dynamically protected cat qubit

Authors: Tian-Le Yang, Pei-Rong Han, Zhen-Biao Yang, Shi-Biao Zheng

Abstract: Dissipatively stabilized cat qubits are promising for fault-tolerant quantum information processing, yet their non-Hermitian (NH) spectral topology remains largely unexplored. We uncover rich Liouvillian exceptional structures in a cat-qubit mode stabilized by two-photon drive (TPD) and engineered two-photon loss, in the presence of single-photon drive (SPD) and single-photon loss. In the paramete… ▽ More Dissipatively stabilized cat qubits are promising for fault-tolerant quantum information processing, yet their non-Hermitian (NH) spectral topology remains largely unexplored. We uncover rich Liouvillian exceptional structures in a cat-qubit mode stabilized by two-photon drive (TPD) and engineered two-photon loss, in the presence of single-photon drive (SPD) and single-photon loss. In the parameter space spanned by SPD strength and detuning, we identify both second- and third-order Liouvillian exceptional points (LEP2s and LEP3s). Remarkably, we show that the phase $θ$ of TPD provides coherent control over these exceptional points: the LEP3 diverges and vanishes at $θ=π/2$, while remaining stable and tunable elsewhere. We introduce a topological invariant based on the winding number of a resultant vector, which robustly identifies LEP3s with unit topological charge. Full master-equation simulations confirm that the system dynamics remains confined to the logical subspace with near-unity fidelity. Our results bridge dissipative stabilization, phase-coherent control, and NH topology, demonstrating controllable higher-order LEPs in open quantum systems. △ Less

Submitted 22 April, 2026; originally announced April 2026.

Comments: 4 figures

Accretion-Mode Transition: The Driver Behind Spectral Changes in Changing-Look AGNs

Authors: Pengyuan Han, Huaiyuan Lu, Bing Lyu, Jiancheng Wu, Qingwen Wu

Abstract: The physical origin of optical changing-look AGNs (CLAGNs), characterized by the appearance or disappearance of broad emission lines, is thought to be mainly driven by the variation of the black-hole (BH) accretion rate. In this work, we explore this issue based on a sample of {224} CLAGNs with UV-to-optical continua, where the UV radiation is more sensitive to the accretion state near the BH hori… ▽ More The physical origin of optical changing-look AGNs (CLAGNs), characterized by the appearance or disappearance of broad emission lines, is thought to be mainly driven by the variation of the black-hole (BH) accretion rate. In this work, we explore this issue based on a sample of {224} CLAGNs with UV-to-optical continua, where the UV radiation is more sensitive to the accretion state near the BH horizon. We find that the luminosity correlation of $L_{3000}$--$L_{5100}$ at 3000$\rm Å$ and 5100$\rm Å$ becomes steeper at low luminosities (e.g., $L_{3000}\lesssim10^{44}\rm erg/s$), where the sources with high luminosities are roughly consistent with the prediction of a standard accretion disk. At lower luminosities, the observations are more consistent with the prediction of a truncated disk. The whole sample has a median bolometric Eddington ratio of $\sim$2.2\%, which is consistent with the critical value for state transition in X-ray binaries. Such transitions can significantly alter the UV-to-optical continuum, largely due to variations in the truncation radius, even when the change in the overall accretion rate is minimal. The deficit of ionization photons resulting from an increase in the truncation radius will lead to the weakening or disappearance of broad lines, which triggers the AGN changing-look. △ Less

Submitted 14 April, 2026; originally announced April 2026.

Comments: 10 pages, 4 figures, accepted by RAA

Thought-Retriever: Don't Just Retrieve Raw Data, Retrieve Thoughts for Memory-Augmented Agentic Systems

Authors: Tao Feng, Pengrui Han, Guanyu Lin, Ge Liu, Jiaxuan You

Abstract: Large language models (LLMs) have transformed AI research thanks to their powerful internal capabilities and knowledge. However, existing LLMs still fail to effectively incorporate the massive external knowledge when interacting with the world. Although retrieval-augmented LLMs are proposed to mitigate the issue, they are still fundamentally constrained by the context length of LLMs, as they can o… ▽ More Large language models (LLMs) have transformed AI research thanks to their powerful internal capabilities and knowledge. However, existing LLMs still fail to effectively incorporate the massive external knowledge when interacting with the world. Although retrieval-augmented LLMs are proposed to mitigate the issue, they are still fundamentally constrained by the context length of LLMs, as they can only retrieve top-K raw data chunks from the external knowledge base which often consists of millions of data chunks. Here we propose Thought-Retriever, a novel model-agnostic algorithm that helps LLMs generate output conditioned on arbitrarily long external data, without being constrained by the context length or number of retrieved data chunks. Our key insight is to let an LLM fully leverage its intermediate responses generated when solving past user queries (thoughts), filtering meaningless and redundant thoughts, organizing them in thought memory, and retrieving the relevant thoughts when addressing new queries. This effectively equips LLM-based agents with a self-evolving long-term memory that grows more capable through continuous interaction. Besides algorithmic innovation, we further meticulously prepare a novel benchmark, AcademicEval, which requires an LLM to faithfully leverage ultra-long context to answer queries based on real-world academic papers. Extensive experiments on AcademicEval and two other public datasets validate that Thought-Retriever remarkably outperforms state-of-the-art baselines, achieving an average increase of at least 7.6% in F1 score and 16% in win rate across various tasks. More importantly, we further demonstrate two exciting findings: (1) Thought-Retriever can indeed help LLM self-evolve after solving more user queries; (2) Thought-Retriever learns to leverage deeper thoughts to answer more abstract user queries. △ Less

Submitted 13 April, 2026; originally announced April 2026.

Journal ref: Transactions on Machine Learning Research (TMLR), 04/2026

PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking

Authors: Jiacheng Bao, Haoran Yang, Yucheng Xin, Junhong Liu, Yuecheng Xu, Han Liang, Pengfei Han, Xiaoguang Ma, Dong Wang, Bin Zhao

Abstract: Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation models are predominantly trained on captured human motion datasets, whose priors assume human biomechanics, actuation, mass distribution, and contact strategies. When such motions are directly retargeted to humanoid robots, the resulting trajectories may satisf… ▽ More Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation models are predominantly trained on captured human motion datasets, whose priors assume human biomechanics, actuation, mass distribution, and contact strategies. When such motions are directly retargeted to humanoid robots, the resulting trajectories may satisfy geometric constraints (e.g., joint limits and pose continuity) and appear kinematically reasonable. However, they frequently violate the physical feasibility required for real-world execution. To address these issues, we present PhyGile, a unified framework that closes the loop between robot-native motion generation and General Motion Tracking (GMT). PhyGile performs physics-prefix-guided robot-native motion generation at inference time, directly generating robot-native motions in a 262-dimensional skeletal space with physics-guided prefixes, thereby eliminating inference-time retargeting artifacts and reducing generation-execution discrepancies. Before physics-prefix adaptation, we train the GMT controller with a curriculum-based mixture-of-experts scheme, followed by post-training on unlabeled motion data to improve robustness over large-scale robot motions. During physics-prefix adaptation, the GMT controller is further fine-tuned with generated objectives under physics-derived prefixes, enabling agile and stable execution of complex motions on real robots. Extensive offline and real-robot experiments demonstrate that PhyGile expands the frontier of text-driven humanoid control, enabling stable tracking of agile, highly difficult whole-body motions that go well beyond walking and low-dynamic motions typically achieved by prior methods. △ Less

Submitted 24 June, 2026; v1 submitted 13 March, 2026; originally announced March 2026.

Fast Physics-Driven Untrained Network for Highly Nonlinear Inverse Scattering Problems

Authors: Yutong Du, Zicheng Liu, Yi Huang, Bazargul Matkerim, Bo Qi, Yali Zong, Peixian Han

Abstract: Untrained neural networks (UNNs) offer high-fidelity electromagnetic inverse scattering reconstruction but are computationally limited by high-dimensional spatial-domain optimization. We propose a Real-Time Physics-Driven Fourier-Spectral (PDF) solver that achieves sub-second reconstruction through spectral-domain dimensionality reduction. By expanding induced currents using a truncated Fourier ba… ▽ More Untrained neural networks (UNNs) offer high-fidelity electromagnetic inverse scattering reconstruction but are computationally limited by high-dimensional spatial-domain optimization. We propose a Real-Time Physics-Driven Fourier-Spectral (PDF) solver that achieves sub-second reconstruction through spectral-domain dimensionality reduction. By expanding induced currents using a truncated Fourier basis, the optimization is confined to a compact low-frequency parameter space supported by scattering measurements. The solver integrates a contraction integral equation (CIE) to mitigate high-contrast nonlinearity and a contrast-compensated operator (CCO) to correct spectral-induced attenuation. Furthermore, a bridge-suppressing loss is formulated to enhance boundary sharpness between adjacent scatterers. Numerical and experimental results demonstrate a 100-fold speedup over state-of-the-art UNNs with robust performance under noise and antenna uncertainties, enabling real-time microwave imaging applications. △ Less

Submitted 14 February, 2026; originally announced February 2026.

LHAASO observation of Mrk 421 during 2021 March - 2024 March: a comprehensive VHE catalog of multi-timescale outbursts and its time average behavior

Authors: The LHAASO Collaboration, Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao, D. Bastieri, X. J. Bi, Y. J. Bi, W. Bian, J. Blunier, A. V. Bukevich, C. M. Cai, Y. Y. Cai, W. Y. Cao, Zhe Cao, J. Chang, J. F. Chang, E. S. Chen, G. H. Chen, H. K. Chen, L. F. Chen, Liang Chen, Long Chen, M. J. Chen, M. L. Chen , et al. (303 additional authors not shown)

Abstract: The Large High Altitude Air Shower Observatory (LHAASO) monitors sources within its field of view for up to 7 hours daily, achieving a duty cycle exceeding 98% and an annual point-source sensitivity of 1.5% Crab Units (CU) in the very high energy (VHE) band. This unbiased sky-survey mode facilitates systematic monitoring and investigation of outburst phenomena. In this paper, we present results fr… ▽ More The Large High Altitude Air Shower Observatory (LHAASO) monitors sources within its field of view for up to 7 hours daily, achieving a duty cycle exceeding 98% and an annual point-source sensitivity of 1.5% Crab Units (CU) in the very high energy (VHE) band. This unbiased sky-survey mode facilitates systematic monitoring and investigation of outburst phenomena. In this paper, we present results from an unprecedented three-year monitoring campaign (March 2021--March 2024) of Mrk421 using LHAASO, spanning energies from 0.4 TeV to 20 TeV. We find that the blazar stayed in a quiescent state in 2021 and became active starting in 2022 with a total of 23 VHE outburst events identified, where the highest observed daily significance reaches $20\,σ$ with a flux equivalent to approximately 3.3~CU. LHAASO's continuous monitoring suggests the flaring occupancy of Mrk~421 to be around 14%. During long-term monitoring, multiwavelength (MWL) variability and correlation analyses are conducted using complementary data from Fermi-LAT, MAXI-GSC, Swift-XRT, and ZTF. A significant correlation ($>3\,σ$) is observed between X-ray and VHE bands with no detectable time lag, while the correlation between GeV and TeV bands is weaker. The flux distribution of the TeV emission during the quiescent state is different from that in the active state, implying the existence of two modes of energy dissipation in the blazar jet. Using simultaneous MWL data, we also analyzed both the long-term and outburst-period SEDs, and discussed the possible origin of the outburst events. △ Less

Submitted 13 February, 2026; originally announced February 2026.

Comments: 34 pages, 20 figures

Mixed-State Topology in Non-Hermitian Systems

Authors: Shou-Bang Yang, Pei-Rong Han, Wen Ning, Fan Wu, Zhen-Biao Yang, Shi-Biao Zheng

Abstract: Non-Hermitian (NH) systems, owing to the existence of exceptional point (or ring and surface), exhibit exotic topological features which are inaccessible in Hermitian systems. While current studies on NH topology has primarily focused on pure states at zero temperature, the topological properties of mixed states remain largely unexplored. In this work, we investigate the mixed-state topology in tw… ▽ More Non-Hermitian (NH) systems, owing to the existence of exceptional point (or ring and surface), exhibit exotic topological features which are inaccessible in Hermitian systems. While current studies on NH topology has primarily focused on pure states at zero temperature, the topological properties of mixed states remain largely unexplored. In this work, we investigate the mixed-state topology in two-dimensional NH systems using the Uhlmann phase and the thermal Uhlmann-Chern number, both structured via the Uhlmann connection at specific temperatures, revealing distinct topological characteristics compared to those of pure states. Furthermore, we extend our analysis to mixed states in three-dimensional Abelian and four-dimensional non-Abelian NH systems, confirming the existence of the higher-order mixed-state topology. Our study establishes a conceptual and practical pathway for exploring topological phenomena in the mixed-state regime of NH physics. △ Less

Submitted 9 April, 2026; v1 submitted 11 February, 2026; originally announced February 2026.

Comments: 7 figures

Steer2Adapt: Dynamically Composing Steering Vectors Elicits Efficient Adaptation of LLMs

Authors: Pengrui Han, Xueqiang Xu, Keyang Xuan, Peiyang Song, Siru Ouyang, Runchu Tian, Yuqing Jiang, Cheng Qian, Pengcheng Jiang, Jiashuo Sun, Junxia Cui, Ming Zhong, Ge Liu, Jiawei Han, Jiaxuan You

Abstract: Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making them inflexible under task variation and inadequate for complex tasks that require multiple coordinated capabilities. To address this limitation, we propose STEER2… ▽ More Activation steering has emerged as a promising approach for efficiently adapting large language models (LLMs) to downstream behaviors. However, most existing steering methods rely on a single static direction per task or concept, making them inflexible under task variation and inadequate for complex tasks that require multiple coordinated capabilities. To address this limitation, we propose STEER2ADAPT, a lightweight framework that adapts LLMs by composing steering vectors rather than learning new ones from scratch. In many domains (e.g., reasoning or safety), tasks share a small set of underlying concept dimensions. STEER2ADAPT captures these dimensions as a reusable, low-dimensional semantic prior subspace, and adapts to new tasks by dynamically discovering a linear combination of basis vectors from only a handful of examples. Experiments across 9 tasks and 3 models in both reasoning and safety domains demonstrate the effectiveness of STEER2ADAPT, achieving an average improvement of 8.2%. Extensive analyses further show that STEER2ADAPT is a data-efficient, stable, and transparent inference-time adaptation method for LLMs. △ Less

Submitted 6 February, 2026; originally announced February 2026.

Large Language Model Reasoning Failures

Authors: Peiyang Song, Pengrui Han, Noah Goodman

Abstract: Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. Despite these advances, significant reasoning failures persist, occurring even in seemingly simple scenarios. To systematically understand and address these shortcomings, we present the first comprehensive survey dedicated to reasoning failures in LLMs. We intro… ▽ More Large Language Models (LLMs) have exhibited remarkable reasoning capabilities, achieving impressive results across a wide range of tasks. Despite these advances, significant reasoning failures persist, occurring even in seemingly simple scenarios. To systematically understand and address these shortcomings, we present the first comprehensive survey dedicated to reasoning failures in LLMs. We introduce a novel categorization framework that distinguishes reasoning into embodied and non-embodied types, with the latter further subdivided into informal (intuitive) and formal (logical) reasoning. In parallel, we classify reasoning failures along a complementary axis into three types: fundamental failures intrinsic to LLM architectures that broadly affect downstream tasks; application-specific limitations that manifest in particular domains; and robustness issues characterized by inconsistent performance across minor variations. For each reasoning failure, we provide a clear definition, analyze existing studies, explore root causes, and present mitigation strategies. By unifying fragmented research efforts, our survey provides a structured perspective on systemic weaknesses in LLM reasoning, offering valuable insights and guiding future research towards building stronger, more reliable, and robust reasoning capabilities. We additionally release a comprehensive collection of research works on LLM reasoning failures, as a GitHub repository at https://github.com/Peiyang-Song/Awesome-LLM-Reasoning-Failures, to provide an easy entry point to this area. △ Less

Submitted 5 February, 2026; originally announced February 2026.

Comments: Repository: https://github.com/Peiyang-Song/Awesome-LLM-Reasoning-Failures. Published at TMLR 2026 with Survey Certification

Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation

Authors: Jiashuo Sun, Pengcheng Jiang, Saizhuo Wang, Jiajun Fan, Heng Wang, Siru Ouyang, Ming Zhong, Yizhu Jiao, Chengsong Huang, Xueqiang Xu, Pengrui Han, Peiran Li, Jiaxin Huang, Ge Liu, Heng Ji, Jiawei Han

Abstract: Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retrievers and rerankers optimize solely for relevance, often selecting either trivial, answer-revealing passages or evidence that lacks the critical information required to answer the question, without considering whether t… ▽ More Retrieval-Augmented Generation (RAG) systems remain brittle under realistic retrieval noise, even when the required evidence appears in the top-K results. A key reason is that retrievers and rerankers optimize solely for relevance, often selecting either trivial, answer-revealing passages or evidence that lacks the critical information required to answer the question, without considering whether the evidence is suitable for the generator. We propose BAR-RAG, which reframes the reranker as a boundary-aware evidence selector that targets the generator's Goldilocks Zone -- evidence that is neither trivially easy nor fundamentally unanswerable for the generator, but is challenging yet sufficient for inference and thus provides the strongest learning signal. BAR-RAG trains the selector with reinforcement learning using generator feedback, and adopts a two-stage pipeline that fine-tunes the generator under the induced evidence distribution to mitigate the distribution mismatch between training and inference. Experiments on knowledge-intensive question answering benchmarks show that BAR-RAG consistently improves end-to-end performance under noisy retrieval, achieving an average gain of 10.3 percent over strong RAG and reranking baselines while substantially improving robustness. Code is publicly avaliable at https://github.com/GasolSun36/BAR-RAG. △ Less

Submitted 3 February, 2026; originally announced February 2026.

Comments: 19 pages, 8 tables, 5 figures

A Model-Robust G-Computation Method for Analyzing Hybrid Control Studies Without Assuming Exchangeability

Authors: Zhiwei Zhang, Peisong Han, Wei Zhang

Abstract: There is growing interest in a hybrid control design for treatment evaluation, where a randomized controlled trial is augmented with external control data from a previous trial or a real world data source. The hybrid control design has the potential to improve efficiency but also carries the risk of introducing bias. The potential bias in a hybrid control study can be mitigated by adjusting for ba… ▽ More There is growing interest in a hybrid control design for treatment evaluation, where a randomized controlled trial is augmented with external control data from a previous trial or a real world data source. The hybrid control design has the potential to improve efficiency but also carries the risk of introducing bias. The potential bias in a hybrid control study can be mitigated by adjusting for baseline covariates that are related to the control outcome. Existing methods that serve this purpose commonly assume that the internal and external control outcomes are exchangeable upon conditioning on a set of measured covariates. Possible violations of the exchangeability assumption can be addressed using a g-computation method with variable selection under a correctly specified outcome regression model. In this article, we note that a particular version of this g-computation method is protected against misspecification of the outcome regression model. This observation leads to a model-robust g-computation method that is remarkably simple and easy to implement, consistent and asymptotically normal under minimal assumptions, and able to improve efficiency by exploiting similarities between the internal and external control groups. The method is evaluated in a simulation study and illustrated using real data from HIV treatment trials. △ Less

Submitted 5 May, 2026; v1 submitted 2 February, 2026; originally announced February 2026.

Exceptional phase transition in a single Kerr-cat qubit

Authors: Pei-Rong Han, Tian-Le Yang, Wen Ning, Hao-Long Zhang, Huifang Kang, Huiye Qiu, Zhen-Biao Yang

Abstract: Exceptional points in non-Hermitian quantum systems give rise to novel genuine quantum phenomena. Recent explorations of exceptional-point-induced quantum phase transitions have extended from discrete-variable to continuous-variable-encoded quantum systems. However, quantum phase transitions driven by Liouvillian exceptional points (LEPs) in continuous-variable platforms remain largely unexplored.… ▽ More Exceptional points in non-Hermitian quantum systems give rise to novel genuine quantum phenomena. Recent explorations of exceptional-point-induced quantum phase transitions have extended from discrete-variable to continuous-variable-encoded quantum systems. However, quantum phase transitions driven by Liouvillian exceptional points (LEPs) in continuous-variable platforms remain largely unexplored. Here, we construct and investigate a Liouvillian exceptional structure based on a driven-dissipative Kerr-cat qubit. Through numerical simulations, we reveal a quantum phase transition occurring at the LEP characterized by a sudden change in dynamical behavior from underdamped oscillations to overdamped relaxations as visualized via Wigner functions and Bloch sphere trajectories. Notably the negativity of the Wigner function serves as a direct signature of genuine quantum coherence unattainable in conventional single-qubit non-Hermitian systems. Furthermore, we introduce the phase difference between the off-diagonal elements of the Liouvillian eigenmatrices as a novel parameter to quantify the transition. Our results establish the Kerr-cat qubit as a novel continuous-variable setting for exploring dissipative quantum criticality and intrinsic non-Hermitian physics. △ Less

Submitted 2 February, 2026; originally announced February 2026.

Comments: 5 figures

PCBSchemaGen: Reward-Guided LLM Code Synthesis for Printed Circuit Boards (PCB) Schematic Design with Structured Verification

Authors: Huanghaohe Zou, Peng Han, Emad Nazerian, Mafu Zhang, Zhicheng Guo, Alex Q. Huang

Abstract: Most LLM code-synthesis benchmarks rely on unit tests as the reward oracle, but PCB schematic design has none: correctness is defined by structured physical constraints over real IC packages and pin-level assignments, per-task golden references are unavailable, and SPICE simulation does not validate schematic-level correctness. We introduce PCBSchemaGen, a training-free inference-time framework th… ▽ More Most LLM code-synthesis benchmarks rely on unit tests as the reward oracle, but PCB schematic design has none: correctness is defined by structured physical constraints over real IC packages and pin-level assignments, per-task golden references are unavailable, and SPICE simulation does not validate schematic-level correctness. We introduce PCBSchemaGen, a training-free inference-time framework that turns a frozen LLM into a verifiable, repairable PCB schematic generator. The framework induces a domain schema from IC datasheets to ground LLM decoding, pairs it with a deterministic 5-layer continuous-reward verifier with pin-level error localization, and refines candidates through a Thompson Sampling arm-acquiring bandit. We evaluate on 2 PCB benchmarks covering 227 real-IC tasks across 22 unified circuit domains, including a public-schematic-derived suite that serves as a fully held-out generalization test (verifier, KG library, and prompts frozen before any evaluation). Under our framework, an open-weight 31B model (Gemma-4-31B) passes 81.3% of PCBBench tasks on average, and the same framework transfers across both benchmarks with zero verifier code changes; a Circuitron-style inference-time prompting baseline on the same Gemma-4-31B backbone collapses on hard system-level designs. This suggests inference-time refinement under a deterministic structural verifier is a general recipe for reference-free LLM code synthesis in domains without unit-test oracles. Our benchmarks and deterministic verifier are publicly available at https://github.com/HZou9/PCBSchemaGen_v2. △ Less

Submitted 17 June, 2026; v1 submitted 30 January, 2026; originally announced February 2026.

Multimodal Benchmark for Safety Assessment in Industrial Inspection Scenarios

Authors: Zeyi Liu, Shuang Liu, Jihai Min, Zhaoheng Zhang, Jun Cen, Pengyu Han, Songqiao Hu, Zihan Meng, Xiao He, Donghua Zhou

Abstract: With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in complex and dynamic industrial sites has become a key bottleneck for deploying predictive maintenance and autonomous inspection. Most public datasets remain limited by simulated data sources, single-modality sensing, or the absence of fine-grained object-level… ▽ More With the rapid development of industrial intelligence and unmanned inspection, reliable perception and safety assessment for AI systems in complex and dynamic industrial sites has become a key bottleneck for deploying predictive maintenance and autonomous inspection. Most public datasets remain limited by simulated data sources, single-modality sensing, or the absence of fine-grained object-level annotations, which prevents robust scene understanding and multimodal safety reasoning for industrial foundation models. To address these limitations, InspecSafe-V1 is released as the first multimodal benchmark dataset for industrial inspection safety assessment that is collected from routine operations of real inspection robots in real-world environments. InspecSafe-V1 covers five representative industrial scenarios, including tunnels, power facilities, sintering equipment, oil and gas petrochemical plants, and coal conveyor trestles. The dataset is constructed from 41 wheeled and rail-mounted inspection robots operating at 2,239 valid inspection sites, yielding 5,013 inspection instances. For each instance, pixel-level segmentation annotations are provided for key objects in visible-spectrum images. In addition, a semantic scene description and a corresponding safety level label are provided according to practical inspection tasks. Seven synchronized sensing modalities are further included, including infrared video, audio, depth point clouds, radar point clouds, gas measurements, temperature, and humidity, to support multimodal anomaly recognition, cross-modal fusion, and comprehensive safety assessment in industrial environments. △ Less

Submitted 30 June, 2026; v1 submitted 28 January, 2026; originally announced January 2026.

Comments: 14 pages, 6 figures, Accepted by Scientific Data

R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning

Authors: Zhizheng Jiang, Kang Zhao, Weikai Xu, Xinkui Lin, Wei Liu, Jian Luan, Shuo Shang, Peng Han

Abstract: Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise in enabling stable advantage estimation without reliance on process-level annotations. However, these methods rely on advantage gaps induced by high-quality samples within the same batch, which makes the training process… ▽ More Large reasoning models (LRMs) aim to solve diverse and complex problems through structured reasoning. Recent advances in group-based policy optimization methods have shown promise in enabling stable advantage estimation without reliance on process-level annotations. However, these methods rely on advantage gaps induced by high-quality samples within the same batch, which makes the training process fragile and inefficient when intra-group advantages collapse under challenging tasks. To address these problems, we propose a reinforcement learning mechanism named \emph{\textbf{R^3}} that along three directions: (1) a \emph{cross-context \underline{\textbf{R}}eplay} strategy that maintains the intra-group advantage by recalling valuable examples from historical trajectories of the same query, (2) an \emph{in-context self-\underline{\textbf{R}}eflection} mechanism enabling models to refine outputs by leveraging past failures, and (3) a \emph{structural entropy \underline{\textbf{R}}anking reward}, which assigns relative rewards to truncated or failed samples by ranking responses based on token-level entropy patterns, capturing both local exploration and global stability. We implement our method on Deepseek-R1-Distill-Qwen-1.5B and train it on the DeepscaleR-40k in the math domain. Experiments demonstrate our method achieves SoTA performance on several math benchmarks, representing significant improvements and fewer reasoning tokens over the base models. Code and model will be released. △ Less

Submitted 27 January, 2026; v1 submitted 27 January, 2026; originally announced January 2026.

DRPG (Decompose, Retrieve, Plan, Generate): An Agentic Framework for Academic Rebuttal

Authors: Peixuan Han, Yingjie Yu, Jingjun Xu, Jiaxuan You

Abstract: Despite the growing adoption of large language models (LLMs) in scientific research workflows, automated support for academic rebuttal, a crucial step in academic communication and peer review, remains largely underexplored. Existing approaches typically rely on off-the-shelf LLMs or simple pipelines, which struggle with long-context understanding and often fail to produce targeted and persuasive… ▽ More Despite the growing adoption of large language models (LLMs) in scientific research workflows, automated support for academic rebuttal, a crucial step in academic communication and peer review, remains largely underexplored. Existing approaches typically rely on off-the-shelf LLMs or simple pipelines, which struggle with long-context understanding and often fail to produce targeted and persuasive responses. In this paper, we propose DRPG, an agentic framework for automatic academic rebuttal generation that operates through four steps: Decompose reviews into atomic concerns, Retrieve relevant evidence from the paper, Plan rebuttal strategies, and Generate responses accordingly. Notably, the Planner in DRPG reaches over 98% accuracy in identifying the most feasible rebuttal direction. Experiments on data from top-tier conferences demonstrate that DRPG significantly outperforms existing rebuttal pipelines and achieves performance beyond the average human level using only an 8B model. Our analysis further demonstrates the effectiveness of the planner design and its value in providing multi-perspective and explainable suggestions. We also showed that DRPG works well in a more complex multi-round setting. These results highlight the effectiveness of DRPG and its potential to provide high-quality rebuttal content and support the scaling of academic discussions. Codes for this work are available at https://github.com/ulab-uiuc/DRPG-RebuttalAgent. △ Less

Submitted 13 April, 2026; v1 submitted 25 January, 2026; originally announced January 2026.

Weather-R1: Logically Consistent Reinforcement Fine-Tuning for Multimodal Reasoning in Meteorology

Authors: Kaiyu Wu, Pucheng Han, Hualong Zhang, Naigeng Wu, Keze Wang

Abstract: While Vision Language Models (VLMs) show advancing reasoning capabilities, their application in meteorology is constrained by a domain gap and a reasoning faithfulness gap. Specifically, mainstream Reinforcement Fine-Tuning (RFT) can induce Self-Contradictory Reasoning (Self-Contra), where the model's reasoning contradicts its final answer, which is unacceptable in such a high-stakes domain. To ad… ▽ More While Vision Language Models (VLMs) show advancing reasoning capabilities, their application in meteorology is constrained by a domain gap and a reasoning faithfulness gap. Specifically, mainstream Reinforcement Fine-Tuning (RFT) can induce Self-Contradictory Reasoning (Self-Contra), where the model's reasoning contradicts its final answer, which is unacceptable in such a high-stakes domain. To address these challenges, we construct WeatherQA, a novel multimodal reasoning benchmark in meteorology. We also propose Logically Consistent Reinforcement Fine-Tuning (LoCo-RFT), which resolves Self-Contra by introducing a logical consistency reward. Furthermore, we introduce Weather-R1, the first reasoning VLM with logical faithfulness in meteorology, to the best of our knowledge. Experiments demonstrate that Weather-R1 improves performance on WeatherQA by 9.8 percentage points over the baseline, outperforming Supervised Fine-Tuning and RFT, and even surpassing the original Qwen2.5-VL-32B. These results highlight the effectiveness of our LoCo-RFT and the superiority of Weather-R1. Our benchmark and code are available at https://github.com/Marcowky/Weather-R1. △ Less

Submitted 20 January, 2026; originally announced January 2026.

Journal ref: ICASSP 2026 - 2026 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, 2026, pp. 4851-4855

Ultralow-noise microwave oscillator via optical frequency division with a co-self-injection-locked miniature Fabry-Perot reference

Authors: Runlin Miao, Chao Zhou, Pan Han, Mingxin Yang, Xing Zou, Ke Wei, Ke Yin, Tian Jiang

Abstract: Optical frequency division (OFD) provides the purest microwaves by down-converting the stability of optical cavity references. State-of-the-art references typically rely on electronic co-Pound-Drever-Hall locking to ultrahigh-Q microresonators-a complex approach that introduces servo bumps and increases footprint. Alternatively, optical co-self-injection-locking (co-SIL) offers inherent simplicity… ▽ More Optical frequency division (OFD) provides the purest microwaves by down-converting the stability of optical cavity references. State-of-the-art references typically rely on electronic co-Pound-Drever-Hall locking to ultrahigh-Q microresonators-a complex approach that introduces servo bumps and increases footprint. Alternatively, optical co-self-injection-locking (co-SIL) offers inherent simplicity but is limited by the large thermo-refractive noise and confined mode volumes of integrated cavities. Here, we demonstrate a two-point OFD-based microwave oscillator that combines an ultrahigh-Q miniature Fabry-Perot cavity with optical co-SIL. Leveraging its low relative phase noise optical reference and combing with an integrated soliton microcomb, the system generates a microwave with phase noise of -147 dBc/Hz at 4 kHz offset (scaled to 10 GHz)-performance rivalling most electronically stabilized systems. This work marries the superior noise floor of ultrahigh-Q cavities with the simplicity of optical locking, providing a compact, cost-effective, and field-deployable path to pure microwaves for next-generation communications, radar and metrology. △ Less

Submitted 12 January, 2026; originally announced January 2026.

Rethinking Knowledge Distillation in Collaborative Machine Learning: Memory, Knowledge, and Their Interactions

Authors: Pengchao Han, Xi Huang, Yi Fang, Guojun Han

Abstract: Collaborative learning has emerged as a key paradigm in large-scale intelligent systems, enabling distributed agents to cooperatively train their models while addressing their privacy concerns. Central to this paradigm is knowledge distillation (KD), a technique that facilitates efficient knowledge transfer among agents. However, the underlying mechanisms by which KD leverages memory and knowledge… ▽ More Collaborative learning has emerged as a key paradigm in large-scale intelligent systems, enabling distributed agents to cooperatively train their models while addressing their privacy concerns. Central to this paradigm is knowledge distillation (KD), a technique that facilitates efficient knowledge transfer among agents. However, the underlying mechanisms by which KD leverages memory and knowledge across agents remain underexplored. This paper aims to bridge this gap by offering a comprehensive review of KD in collaborative learning, with a focus on the roles of memory and knowledge. We define and categorize memory and knowledge within the KD process and explore their interrelationships, providing a clear understanding of how knowledge is extracted, stored, and shared in collaborative settings. We examine various collaborative learning patterns, including distributed, hierarchical, and decentralized structures, and provide insights into how memory and knowledge dynamics shape the effectiveness of KD in collaborative learning. Particularly, we emphasize task heterogeneity in distributed learning pattern covering federated learning (FL), multi-agent domain adaptation (MADA), federated multi-modal learning (FML), federated continual learning (FCL), federated multi-task learning (FMTL), and federated graph knowledge embedding (FKGE). Additionally, we highlight model heterogeneity, data heterogeneity, resource heterogeneity, and privacy concerns of these tasks. Our analysis categorizes existing work based on how they handle memory and knowledge. Finally, we discuss existing challenges and propose future directions for advancing KD techniques in the context of collaborative learning. △ Less

Submitted 22 December, 2025; originally announced December 2025.

Comments: Published in IEEE TNSE

Cygnus X-3: A variable petaelectronvolt gamma-ray source

Authors: The LHAASO Collaboration, Zhen Cao, F. Aharonian, Y. X. Bai, Y. W. Bao, D. Bastieri, X. J. Bi, Y. J. Bi, W. Bian, J. Blunier, A. V. Bukevich, C. M. Cai, Y. Y. Cai, W. Y. Cao, Zhe Cao, J. Chang, J. F. Chang, E. S. Chen, G. H. Chen, H. K. Chen, L. F. Chen, Liang Chen, Long Chen, M. J. Chen, M. L. Chen , et al. (306 additional authors not shown)

Abstract: We report the discovery of variable $γ$-rays up to petaelectronvolt from Cygnus X-3, an iconic X-ray binary. The $γ$-ray signal was detected with a statistical significance of approximately 10 $σ$ by the Large High Altitude Air Shower Observatory (LHAASO). Its intrinsic spectral energy distribution (SED), extending from 0.06 to 3.7 PeV, shows a pronounced rise toward 1 PeV after accounting for abs… ▽ More We report the discovery of variable $γ$-rays up to petaelectronvolt from Cygnus X-3, an iconic X-ray binary. The $γ$-ray signal was detected with a statistical significance of approximately 10 $σ$ by the Large High Altitude Air Shower Observatory (LHAASO). Its intrinsic spectral energy distribution (SED), extending from 0.06 to 3.7 PeV, shows a pronounced rise toward 1 PeV after accounting for absorption by the cosmic microwave background radiation. We find variability on month-long timescales at a significance of $8.6 σ$, coinciding with a high state of the GeV gamma-ray flux detected by the Fermi-LAT. This,together with a 3.2$σ$ evidence for orbital modulation, suggests that the PeV $γ$-rays originate within, or in close proximity to, the binary system itself. The observed energy spectrum and temporal modulation can be naturally explained by $γ$-ray production through photomeson processes in the innermost region of the relativistic jet, where protons need to be accelerated to tens of PeV energies. △ Less

Submitted 12 April, 2026; v1 submitted 18 December, 2025; originally announced December 2025.

Comments: Submitted to NSR

Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skills

Authors: Pengcheng Jiang, Jiacheng Lin, Zhiyi Shi, Zifeng Wang, Luxi He, Yichen Wu, Ming Zhong, Peiyang Song, Qizheng Zhang, Heng Wang, Xueqiang Xu, Hanwen Xu, Pengrui Han, Dylan Zhang, Jiashuo Sun, Chaoqi Yang, Kun Qian, Tian Wang, Changran Hu, Manling Li, Quanzheng Li, Hao Peng, Sheng Wang, Jingbo Shang, Chao Zhang , et al. (9 additional authors not shown)

Abstract: Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented acro… ▽ More Large language model (LLM) agents are moving beyond prompting alone. ChatGPT marked the rise of general-purpose LLM assistants, DeepSeek showed that on-policy reinforcement learning with verifiable rewards can improve reasoning and tool use, and OpenClaw highlights a newer direction in which agents accumulate persistent memory and reusable skills. Yet the research landscape remains fragmented across post-training, retrieval, memory, and skill systems. This survey studies these developments under a single notion of \emph{adaptation}: improving an agent, its tools, or their interaction after pretraining. We organize the field with a four-paradigm framework spanning agent adaptation and tool adaptation. On the agent side, A1 (tool-execution-signaled) and A2 (agent-output-signaled) improve the agent itself through supervised fine-tuning, preference optimization, and reinforcement learning with verifiable rewards. On the tool side, T1 (agent-agnostic) provides reusable pre-trained modules any agent can call, while T2 (agent-supervised) uses the agent's outputs to train memory systems, skill libraries, or lightweight subagents. Using this framework, we review post-training methods, adaptive memory architectures, and agent skills; compare their trade-offs in cost, flexibility, and generalization; and summarize evaluation practices across deep research, software development, computer use, and drug discovery. We conclude by outlining open problems in agent-tool co-adaptation, continual learning, safety, and efficient deployment. △ Less

Submitted 9 March, 2026; v1 submitted 18 December, 2025; originally announced December 2025.