paper-with-me

Papers

Rethinking the Design of Reinforcement Learning-Based Deep Research Agents

2025-10-17 · Yi Wan, Jiuqi Wang, Liam Li, Jinsong Liu, Ruihao Zhu, Zheqing Zhu arxiv

Large language models (LLMs) augmented with external tools are increasingly deployed as deep research agents that gather, reason over, and synthesize web information to answer complex queries. Although recent open-source systems achieve strong empirical performance via reinforcement learning from web interactions, the impact of key design choices remains under-explored. We formalize deep research as reinforcement learning in an episodic finite Markov decision process and construct a competitive baseline agent grounded in this formulation. Building on this foundation, we systematically examine critical design decisions at both training and inference time and identify four factors that substantially improve performance: replacing rule-based rewards with AI feedback from an LLM judge, fine-tuning with the on-policy RLOO algorithm instead of the off-policy GRPO algorithm, filtering low-quality training samples, and employing an error-tolerant test-time rollout strategy. Together, these design choices yield a deep research agent that establishes state-of-the-art performance among 7B-scale agents when evaluated across ten widely used benchmarks.

📄 PDF Abstract BibTeX arXiv:2510.15862

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Rethinking Supervised Learning and Reinforcement Learning in Task-Oriented Dialogue Systems

2020-09-21 · Findings of the Association for Computational Linguistics 2020 · Ziming Li, Julia Kiseleva, Maarten de Rijke

Dialogue policy learning for task-oriented dialogue systems has enjoyed great progress recently mostly through employing reinforcement learning methods. However, these approaches have become very sophisticated. It is tim…

DecoderMulti-Label ClassificationMUlTI-LABEL-ClASSIFICATIONreinforcement-learning+3

Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models

2019-02-23 · NAACL 2019 6 · Tiancheng Zhao, Kaige Xie, Maxine Eskenazi

Defining action spaces for conversational agents and optimizing their decision-making process with reinforcement learning is an enduring challenge. Common practice has been to use handcrafted dialog acts, or the output v…

Decision MakingDialogue GenerationDialogue ManagementGoal-Oriented Dialogue Systems+3

The Tool Illusion: Rethinking Tool Use in Web Agents

2026-04-03 · Renze Lou, Baolin Peng, Wenlin Yao, Qianhui Wu 외 arxiv

As web agents rapidly evolve, an increasing body of work has moved beyond conventional atomic browser interactions and explored tool use as a higher-level action paradigm. Although prior studies have shown the promise of…

Rethinking the Foundations for Continual Reinforcement Learning

2025-04-10 · Michael Bowling, Esraa Elelimy

Algorithms and approaches for continual reinforcement learning have gained increasing attention. Much of this early progress rests on the foundations and standard practices of traditional reinforcement learning, without …

Continual Learningreinforcement-learningReinforcement Learning

Rethinking Agentic Reinforcement Learning In Large Language Models

2026-04-30 · Fangming Cui, Ruixiao Zhu, Cheng Fang, Sunan Li 외 arxiv

Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the advent of powerful Large Language Models (LL…

Reinforcement Learning