paper-with-me

Papers

WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback

2025-05-26 · Minda Hu, Tianqing Fang, Jianshu Zhang, Junyu Ma, Zhisong Zhang, Jingyan Zhou, Hongming Zhang, Haitao Mi, Dong Yu, Irwin King

Web agents powered by Large Language Models (LLMs) show promise for next-generation AI, but their limited reasoning in uncertain, dynamic web environments hinders robust deployment. In this paper, we identify key reasoning skills essential for effective web agents, i.e., reflection & lookahead, branching, and rollback, and curate trajectory data that exemplifies these abilities by reconstructing the agent's (inference-time) reasoning algorithms into chain-of-thought rationales. We conduct experiments in the agent self-improving benchmark, OpenWebVoyager, and demonstrate that distilling salient reasoning patterns into the backbone LLM via simple fine-tuning can substantially enhance its performance. Our approach yields significant improvements across multiple benchmarks, including WebVoyager, Mind2web-live, and SimpleQA (web search), highlighting the potential of targeted reasoning skill enhancement for web agents.

📄 PDF Abstract BibTeX arXiv:2505.20013

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains

2026-03-01 · Xuying Ning, Dongqi Fu, Tianxin Wei, Mengting Ai 외 arxiv

With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve-then-generate paradigm toward more soph…

Multimodal Reasoning

GroupDebate: Enhancing the Efficiency of Multi-Agent Debate Using Group Discussion

2024-09-21 · Tongxuan Liu, Xingyu Wang, Weizhe Huang, Wenjiang Xu 외

In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities across diverse NLP tasks. Extensive research has explored how to enhance the logical reasoning abilities such as Chain-of-Thought, C…

Logical Reasoning

Efficient Agentic Reasoning Through Self-Regulated Simulative Planning

2026-05-21 · Mingkai Deng, Jinyu Hou, Lara Sá Neves, Varad Pimpalkhute 외 arxiv

How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expecting planning to emerge implicitly. With…

Reinforcement Learning

Logic Agent: Enhancing Validity with Logic Rule Invocation

2024-04-28 · Hanmeng Liu, Zhiyang Teng, Chaoli Zhang, Yue Zhang

Chain-of-Thought (CoT) prompting has emerged as a pivotal technique for augmenting the inferential capabilities of language models during reasoning tasks. Despite its advancements, CoT often grapples with challenges in v…

InformativenessNavigate

Coordinating Search-Informed Reasoning and Reasoning-Guided Search in Claim Verification

2025-06-09 · Qisheng Hu, Quanyu Long, Wenya Wang

Multi-hop claim verification is inherently challenging, requiring multi-step reasoning to construct verification chains while iteratively searching for information to uncover hidden bridging facts. This process is fundam…

Claim Verification