-
Modeling Distinct Human Interaction in Web Agents
Authors:
Faria Huq,
Zora Zhiruo Wang,
Zhanqiu Guo,
Venu Arvind Arangarajan,
Tianyue Ou,
Frank Xu,
Shuyan Zhou,
Graham Neubig,
Jeffrey P. Bigham
Abstract:
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeli…
▽ More
Despite rapid progress in autonomous web agents, human involvement remains essential for shaping preferences and correcting agent behavior as tasks unfold. However, current agentic systems lack a principled understanding of when and why humans intervene, often proceeding autonomously past critical decision points or requesting unnecessary confirmation. In this work, we introduce the task of modeling human intervention to support collaborative web task execution. We collect CowCorpus, a dataset of 400 real-user web navigation trajectories containing over 4,200 interleaved human and agent actions. We identify four distinct patterns of user interaction with agents -- hands-off supervision, hands-on oversight, collaborative task-solving, and full user takeover. Leveraging these insights, we train language models (LMs) to anticipate when users are likely to intervene based on their interaction styles, yielding a 61.4-63.4% improvement in intervention prediction accuracy over base LMs. Finally, we deploy these intervention-aware models in live web navigation agents and evaluate them in a user study, finding a 36.8% increase in user-rated agent usefulness. Together, our results show structured modeling of human intervention leads to more adaptive, collaborative agents.
△ Less
Submitted 7 July, 2026; v1 submitted 19 February, 2026;
originally announced February 2026.
-
On the Regulatory Potential of User Interfaces for AI Agent Governance
Authors:
K. J. Kevin Feng,
Tae Soo Kim,
Rock Yuren Pang,
Faria Huq,
Tal August,
Amy X. Zhang
Abstract:
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target system-level safeguards (e.g., prompt injection monitors) or agent infrastructure (e.g., agent IDs). In this work, we explore a complementary approach: regulating use…
▽ More
AI agents that take actions in their environment autonomously over extended time horizons require robust governance interventions to curb their potentially consequential risks. Prior proposals for governing AI agents primarily target system-level safeguards (e.g., prompt injection monitors) or agent infrastructure (e.g., agent IDs). In this work, we explore a complementary approach: regulating user interfaces of AI agents as a way of enforcing transparency and behavioral requirements that then demand changes at the system and/or infrastructure levels. Specifically, we analyze 22 existing agentic systems to identify UI elements that play key roles in human-agent interaction and communication. We then synthesize those elements into six high-level interaction design patterns that hold regulatory potential (e.g., requiring agent memory to be editable). We conclude with policy recommendations based on our analysis. Our work exposes a new surface for regulatory action that supplements previous proposals for practical AI agent governance.
△ Less
Submitted 30 November, 2025;
originally announced December 2025.
-
AI-Mediated Communication Reshapes Social Structure in Opinion-Diverse Groups
Authors:
Faria Huq,
Elijah L. Claggett,
Hirokazu Shirado
Abstract:
Group segregation or cohesion can emerge from micro-level communication, and AI-assisted messaging may shape this process. Here, we report a preregistered online experiment (N = 557 across 60 sessions) in which participants discussed controversial political topics over multiple rounds and could freely change groups. Some participants received real-time message suggestions from a large language mod…
▽ More
Group segregation or cohesion can emerge from micro-level communication, and AI-assisted messaging may shape this process. Here, we report a preregistered online experiment (N = 557 across 60 sessions) in which participants discussed controversial political topics over multiple rounds and could freely change groups. Some participants received real-time message suggestions from a large language model (LLM), either personalized to their stance (individual assistance) or incorporating their group members' perspectives (relational assistance). We find that small variations in AI-mediated communication cascade into macro-level differences in group composition. Participants with individual assistance send more messages and show greater stance-based clustering, whereas those with relational assistance use more receptive language and form more heterogeneous ties. Hybrid expressive processes-jointly produced by humans and AI-can reshape collective organization. The patterns of structural division and cohesion depend on how AI incorporates users' interaction context.
△ Less
Submitted 25 November, 2025; v1 submitted 24 October, 2025;
originally announced October 2025.
-
CowPilot: A Framework for Autonomous and Human-Agent Collaborative Web Navigation
Authors:
Faria Huq,
Zora Zhiruo Wang,
Frank F. Xu,
Tianyue Ou,
Shuyan Zhou,
Jeffrey P. Bigham,
Graham Neubig
Abstract:
While much work on web agents emphasizes the promise of autonomously performing tasks on behalf of users, in reality, agents often fall short on complex tasks in real-world contexts and modeling user preference. This presents an opportunity for humans to collaborate with the agent and leverage the agent's capabilities effectively. We propose CowPilot, a framework supporting autonomous as well as h…
▽ More
While much work on web agents emphasizes the promise of autonomously performing tasks on behalf of users, in reality, agents often fall short on complex tasks in real-world contexts and modeling user preference. This presents an opportunity for humans to collaborate with the agent and leverage the agent's capabilities effectively. We propose CowPilot, a framework supporting autonomous as well as human-agent collaborative web navigation, and evaluation across task success and task efficiency. CowPilot reduces the number of steps humans need to perform by allowing agents to propose next steps, while users are able to pause, reject, or take alternative actions. During execution, users can interleave their actions with the agent by overriding suggestions or resuming agent control when needed. We conducted case studies on five common websites and found that the human-agent collaborative mode achieves the highest success rate of 95% while requiring humans to perform only 15.2% of the total steps. Even with human interventions during task execution, the agent successfully drives up to half of task success on its own. CowPilot can serve as a useful tool for data collection and agent evaluation across websites, which we believe will enable research in how users and agents can work together. Video demonstrations are available at https://oaishi.github.io/cowpilot.html
△ Less
Submitted 27 February, 2026; v1 submitted 27 January, 2025;
originally announced January 2025.
-
DreamStruct: Understanding Slides and User Interfaces via Synthetic Data Generation
Authors:
Yi-Hao Peng,
Faria Huq,
Yue Jiang,
Jason Wu,
Amanda Xin Yue Li,
Jeffrey Bigham,
Amy Pavel
Abstract:
Enabling machines to understand structured visuals like slides and user interfaces is essential for making them accessible to people with disabilities. However, achieving such understanding computationally has required manual data collection and annotation, which is time-consuming and labor-intensive. To overcome this challenge, we present a method to generate synthetic, structured visuals with ta…
▽ More
Enabling machines to understand structured visuals like slides and user interfaces is essential for making them accessible to people with disabilities. However, achieving such understanding computationally has required manual data collection and annotation, which is time-consuming and labor-intensive. To overcome this challenge, we present a method to generate synthetic, structured visuals with target labels using code generation. Our method allows people to create datasets with built-in labels and train models with a small number of human-annotated examples. We demonstrate performance improvements in three tasks for understanding slides and UIs: recognizing visual elements, describing visual content, and classifying visual content types.
△ Less
Submitted 30 September, 2024;
originally announced October 2024.
-
NoTeeline: Supporting Real-Time, Personalized Notetaking with LLM-Enhanced Micronotes
Authors:
Faria Huq,
Abdus Samee,
David Chuan-en Lin,
Xiaodi Alice Tang,
Jeffrey P. Bigham
Abstract:
Taking notes quickly while effectively capturing key information can be challenging, especially when watching videos that present simultaneous visual and auditory streams. Manually taken notes often miss crucial details due to the fast-paced nature of the content, while automatically generated notes fail to incorporate user preferences and discourage active engagement with the content. To address…
▽ More
Taking notes quickly while effectively capturing key information can be challenging, especially when watching videos that present simultaneous visual and auditory streams. Manually taken notes often miss crucial details due to the fast-paced nature of the content, while automatically generated notes fail to incorporate user preferences and discourage active engagement with the content. To address this, we propose an interactive system, NoTeeline, for supporting real-time, personalized notetaking. Given micronotes, NoTeeline automatically expands them into full-fledged notes using a Large Language Model (LLM). The generated notes build on the content of micronotes by adding relevant details while maintaining consistency with the user's writing style. In a within-subjects study (n=12), we found that NoTeeline creates high-quality notes that capture the essence of participant micronotes with 93.2% factual correctness and accurately align with participant writing style (8.33% improvement). Using NoTeeline, participants could capture their desired notes with significantly reduced mental effort, writing 47.0% less text and completing their notes in 43.9% less time compared to a manual notetaking baseline. Our results suggest that NoTeeline enables users to integrate LLM assistance in a familiar notetaking workflow while ensuring consistency with their preferences - providing an example of how to address broader challenges in designing AI-assisted tools to augment human capabilities without compromising user autonomy and personalization.
△ Less
Submitted 30 January, 2025; v1 submitted 24 September, 2024;
originally announced September 2024.
-
"This really lets us see the entire world:" Designing a conversational telepresence robot for homebound older adults
Authors:
Yaxin Hu,
Laura Stegner,
Yasmine Kotturi,
Caroline Zhang,
Yi-Hao Peng,
Faria Huq,
Yuhang Zhao,
Jeffrey P. Bigham,
Bilge Mutlu
Abstract:
In this paper, we explore the design and use of conversational telepresence robots to help homebound older adults interact with the external world. An initial needfinding study (N=8) using video vignettes revealed older adults' experiential needs for robot-mediated remote experiences such as exploration, reminiscence and social participation. We then designed a prototype system to support these go…
▽ More
In this paper, we explore the design and use of conversational telepresence robots to help homebound older adults interact with the external world. An initial needfinding study (N=8) using video vignettes revealed older adults' experiential needs for robot-mediated remote experiences such as exploration, reminiscence and social participation. We then designed a prototype system to support these goals and conducted a technology probe study (N=11) to garner a deeper understanding of user preferences for remote experiences. The study revealed user interactive patterns in each desired experience, highlighting the need of robot guidance, social engagements with the robot and the remote bystanders. Our work identifies a novel design space where conversational telepresence robots can be used to foster meaningful interactions in the remote physical environment. We offer design insights into the robot's proactive role in providing guidance and using dialogue to create personalized, contextualized and meaningful experiences.
△ Less
Submitted 23 May, 2024;
originally announced May 2024.
-
"What's important here?": Opportunities and Challenges of Using LLMs in Retrieving Information from Web Interfaces
Authors:
Faria Huq,
Jeffrey P. Bigham,
Nikolas Martelaro
Abstract:
Large language models (LLMs) that have been trained on a corpus that includes large amount of code exhibit a remarkable ability to understand HTML code. As web interfaces are primarily constructed using HTML, we design an in-depth study to see how LLMs can be used to retrieve and locate important elements for a user given query (i.e. task description) in a web interface. In contrast with prior wor…
▽ More
Large language models (LLMs) that have been trained on a corpus that includes large amount of code exhibit a remarkable ability to understand HTML code. As web interfaces are primarily constructed using HTML, we design an in-depth study to see how LLMs can be used to retrieve and locate important elements for a user given query (i.e. task description) in a web interface. In contrast with prior works, which primarily focused on autonomous web navigation, we decompose the problem as an even atomic operation - Can LLMs identify the important information in the web page for a user given query? This decomposition enables us to scrutinize the current capabilities of LLMs and uncover the opportunities and challenges they present. Our empirical experiments show that while LLMs exhibit a reasonable level of performance in retrieving important UI elements, there is still a substantial room for improvement. We hope our investigation will inspire follow-up works in overcoming the current challenges in this domain.
△ Less
Submitted 11 December, 2023;
originally announced December 2023.
-
Riemannian Functional Map Synchronization for Probabilistic Partial Correspondence in Shape Networks
Authors:
Faria Huq,
Adrish Dey,
Sahra Yusuf,
Dena Bazazian,
Tolga Birdal,
Nina Miolane
Abstract:
We consider the problem of graph-matching on a network of 3D shapes with uncertainty quantification. We assume that the pairwise shape correspondences are efficiently represented as \emph{functional maps}, that match real-valued functions defined over pairs of shapes. By modeling functional maps between nearly isometric shapes as elements of the Lie group $SO(n)$, we employ \emph{synchronization}…
▽ More
We consider the problem of graph-matching on a network of 3D shapes with uncertainty quantification. We assume that the pairwise shape correspondences are efficiently represented as \emph{functional maps}, that match real-valued functions defined over pairs of shapes. By modeling functional maps between nearly isometric shapes as elements of the Lie group $SO(n)$, we employ \emph{synchronization} to enforce cycle consistency of the collection of functional maps over the graph, hereby enhancing the accuracy of the individual maps. We further introduce a tempered Bayesian probabilistic inference framework on $SO(n)$. Our framework enables: (i) synchronization of functional maps as maximum-a-posteriori estimation on the Riemannian manifold of functional maps, (ii) sampling the solution space in our energy based model so as to quantify uncertainty in the synchronization problem. We dub the latter \emph{Riemannian Langevin Functional Map (RLFM) Sampler}. Our experiments demonstrate that constraining the synchronization on the Riemannian manifold $SO(n)$ improves the estimation of the functional maps, while our RLFM sampler provides for the first time an uncertainty quantification of the results.
△ Less
Submitted 3 January, 2023; v1 submitted 29 November, 2021;
originally announced November 2021.
-
Static and Animated 3D Scene Generation from Free-form Text Descriptions
Authors:
Faria Huq,
Nafees Ahmed,
Anindya Iqbal
Abstract:
Generating coherent and useful image/video scenes from a free-form textual description is technically a very difficult problem to handle. Textual description of the same scene can vary greatly from person to person, or sometimes even for the same person from time to time. As the choice of words and syntax vary while preparing a textual description, it is challenging for the system to reliably prod…
▽ More
Generating coherent and useful image/video scenes from a free-form textual description is technically a very difficult problem to handle. Textual description of the same scene can vary greatly from person to person, or sometimes even for the same person from time to time. As the choice of words and syntax vary while preparing a textual description, it is challenging for the system to reliably produce a consistently desirable output from different forms of language input. The prior works of scene generation have been mostly confined to rigorous sentence structures of text input which restrict the freedom of users to write description. In our work, we study a new pipeline that aims to generate static as well as animated 3D scenes from different types of free-form textual scene description without any major restriction. In particular, to keep our study practical and tractable, we focus on a small subspace of all possible 3D scenes, containing various combinations of cube, cylinder and sphere. We design a two-stage pipeline. In the first stage, we encode the free-form text using an encoder-decoder neural architecture. In the second stage, we generate a 3D scene based on the generated encoding. Our neural architecture exploits state-of-the-art language model as encoder to leverage rich contextual encoding and a new multi-head decoder to predict multiple features of an object in the scene simultaneously. For our experiments, we generate a large synthetic data-set which contains 13,00,000 and 14,00,000 samples of unique static and animated scene descriptions, respectively. We achieve 98.427% accuracy on test data set in detecting the 3D objects features successfully. Our work shows a proof of concept of one approach towards solving the problem, and we believe with enough training data, the same pipeline can be expanded to handle even broader set of 3D scene generation problems.
△ Less
Submitted 28 November, 2020; v1 submitted 4 October, 2020;
originally announced October 2020.
-
Review4Repair: Code Review Aided Automatic Program Repairing
Authors:
Faria Huq,
Masum Hasan,
Mahim Anzum Haque Pantho,
Sazan Mahbub,
Anindya Iqbal,
Toufique Ahmed
Abstract:
Context: Learning-based automatic program repair techniques are showing promise to provide quality fix suggestions for detected bugs in the source code of the software. These tools mostly exploit historical data of buggy and fixed code changes and are heavily dependent on bug localizers while applying to a new piece of code. With the increasing popularity of code review, dependency on bug localize…
▽ More
Context: Learning-based automatic program repair techniques are showing promise to provide quality fix suggestions for detected bugs in the source code of the software. These tools mostly exploit historical data of buggy and fixed code changes and are heavily dependent on bug localizers while applying to a new piece of code. With the increasing popularity of code review, dependency on bug localizers can be reduced. Besides, the code review-based bug localization is more trustworthy since reviewers' expertise and experience are reflected in these suggestions.
Objective: The natural language instructions scripted on the review comments are enormous sources of information about the bug's nature and expected solutions. However, none of the learning-based tools has utilized the review comments to fix programming bugs to the best of our knowledge. In this study, we investigate the performance improvement of repair techniques using code review comments.
Method: We train a sequence-to-sequence model on 55,060 code reviews and associated code changes. We also introduce new tokenization and preprocessing approaches that help to achieve significant improvement over state-of-the-art learning-based repair techniques.
Results: We boost the top-1 accuracy by 20.33% and top-10 accuracy by 34.82%. We could provide a suggestion for stylistics and non-code errors unaddressed by prior techniques.
Conclusion: We believe that the automatic fix suggestions along with code review generated by our approach would help developers address the review comment quickly and correctly and thus save their time and effort.
△ Less
Submitted 6 October, 2020; v1 submitted 4 October, 2020;
originally announced October 2020.
-
Impact on the Productivity of Remotely Working IT Professionals of Bangladesh during the Coronavirus Disease 2019
Authors:
Kishan Kumar Ganguly,
Noshin Tahsin,
Mridha Md. Nafis Fuad,
Toukir Ahammed,
Moumita Asad,
Syed Fatiul Huq,
A. T. M. Fazlay Rabbi,
Kazi Sakib
Abstract:
Similar to the rest of the world, the recent pandemic situation has forced the IT professionals of Bangladesh to adopt remote work. The aim of this study is to find out whether remote work can be continued even after the lockdown is lifted. As work from home may change various productivity related aspects of the employees, i.e., team dynamics and company dynamics, it is necessary to understand the…
▽ More
Similar to the rest of the world, the recent pandemic situation has forced the IT professionals of Bangladesh to adopt remote work. The aim of this study is to find out whether remote work can be continued even after the lockdown is lifted. As work from home may change various productivity related aspects of the employees, i.e., team dynamics and company dynamics, it is necessary to understand the nature of the change during WFH. Conducting a survey, we asked the IT professionals of Bangladesh how they perceive their level of productivity during WFH and how the factors related to productivity have changed. We analyzed the change and identified the areas affected by WFH. We discovered that resource and workspace related issues, emotional well-being of the employees have been hampered the most during WFH. We believe that the findings from this study will help to decide how to resolve those issues and will help to understand whether WFH can be continued even after the lockdown is lifted.
△ Less
Submitted 11 September, 2020; v1 submitted 26 August, 2020;
originally announced August 2020.