Generalist web agents have demonstrated remarkable potential in autonomously completing
a wide range of tasks on real websites, significantly boosting human productivity. However, …

As large language models (LLMs) become increasingly prevalent and integrated into
autonomous systems, ensuring their safety is imperative. Despite significant strides toward safety …

This paper presents ChatCounselor, a large language model (LLM) solution designed to
provide mental health support. Unlike generic chatbots, ChatCounselor is distinguished by its …

Modern generative search engines enhance the reliability of large language model (LLM)
responses by providing cited evidence. However, evaluating the answer’s attribution, ie, …

The advancements of large language models (LLMs) have piqued growing interest in
developing LLM-based language agents to automate scientific discovery end-to-end, which has …

This paper introduces v0.5 of the AI Safety Benchmark, which has been created by the
MLCommons AI Safety Working Group. The AI Safety Benchmark has been designed to assess …

A long-term goal of language agents is to learn and improve through their own experience,
ultimately outperforming humans in complex, real-world tasks. However, training agents from …

… Zeyi Liao provided the benign task formulation used … Zeyi Liao and Linxi Jiang led the main
code implementation for the RedTeamCUA framework and sandbox construction. Zeyi Liao …

Agentic search such as Deep Research systems-where agents autonomously browse the
web, synthesize information, and return comprehensive citation-backed answers-represents a …

Vision Language Models (VLMs) have revolutionized the creation of generalist web agents,
empowering them to autonomously complete diverse tasks on real-world websites, thereby …