相关论文: Go-Browse: Training Web Agents with Structured Exp…

Learning in environments with large state and action spaces, and sparse rewards, can hinder a Reinforcement Learning (RL) agent's learning through trial-and-error. For instance, following natural language instructions on the Web (such as…

From professional research to everyday planning, many tasks are bottlenecked by wide-scale information seeking, which is more repetitive than cognitively complex. With the rapid development of Large Language Models (LLMs), automated search…

Web browsers are a portal to the internet, where much of human activity is undertaken. Thus, there has been significant research work in AI agents that interact with the internet through web browsing. However, there is also another…

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…

Modern code intelligence agents operate in contexts exceeding 1 million tokens--far beyond the scale where humans manually locate relevant files. Yet agents consistently fail to discover architecturally critical files when solving…

Recent agentic search systems have made substantial progress by emphasising deep, multi-step reasoning. However, this focus often overlooks the challenges of wide-scale information synthesis, where agents must aggregate large volumes of…

Web agents require massive trajectories to generalize, yet real-world training is constrained by network latency, rate limits, and safety risks. We introduce \textbf{WebWorld} series, the first open-web simulator trained at scale. While…

General-purpose computer-use agents have shown impressive performance across diverse digital environments. However, our new benchmark, OSExpert-Eval, indicates they remain far less helpful than human experts. Although inference-time scaling…

We study the use of large language model-based agents for interacting with software via web browsers. Unlike prior work, we focus on measuring the agents' ability to perform tasks that span the typical daily work of knowledge workers…

Current evaluation of web agents largely reduces to binary success metrics or conformity to a single reference trajectory, ignoring the structural diversity present in benchmark datasets. We present WebGraphEval, a framework that abstracts…

The rise of generative AI search engines is disrupting traditional SEO, with Gartner predicting 25% reduction in conventional search usage by 2026. This necessitates new approaches for web content visibility in AI-driven search…

With the advancement of vision-language models, web automation has made significant progress. However, deploying autonomous agents in real-world settings remains challenging, primarily due to site heterogeneity, where generalist models lack…

We present BrowseComp, a simple yet challenging benchmark for measuring the ability for agents to browse the web. BrowseComp comprises 1,266 questions that require persistently navigating the internet in search of hard-to-find, entangled…

This work presents an exploration and imitation-learning-based agent capable of state-of-the-art performance in playing text-based computer games. Text-based computer games describe their world to the player through natural language and…

Effective information seeking in the vast and ever-growing digital landscape requires balancing expansive search with strategic reasoning. Current large language model (LLM)-based agents struggle to achieve this balance due to limitations…

Recent success in large multimodal models (LMMs) has sparked promising applications of agents capable of autonomously completing complex web tasks. While open-source LMM agents have made significant advances in offline evaluation…

Web agents, which couple language models with browsing and tool-use capabilities, show promise as open web assistants. Yet progress is increasingly limited by the lack of scalable, process-level supervision. Existing benchmarks are largely…

Large Language Model (LLM) web agents often struggle with long-horizon web navigation and web task completion in new websites, producing inefficient action sequences unless fine-tuned on environment-specific data. We show that…

Existing browser agent benchmarks face a fundamental trilemma: real-website benchmarks lack reproducibility due to content drift, controlled environments sacrifice realism by omitting real-web noise, and both require costly manual curation…

As LLM-based agents are deployed in increasingly complex real-world settings, existing benchmarks underrepresent key challenges such as enforcing global constraints, coordinating multi-tool reasoning, and adapting to evolving user behavior…