paper-with-me

홈 › Papers

DSPO: Stable and Efficient Policy Optimization for Agentic Search and Reasoning

2025-10-10 · Chenyang Gu, Yewen Pu, Bruce Yang, Xiaofan Li, Huan Gao arxiv

Enhancing LLMs with the ability to actively search external knowledge is crucial for complex and real-world tasks. Current approaches either rely on prompting to elicit the model's innate agent capabilities, or suffer from performance ceilings and collapse when applying RL to complex interactive tasks, leaving their true agentic potential untapped. To address this, we introduce \textbf{D}ynamic-filter \textbf{S}equence-level \textbf{P}olicy \textbf{O}ptimization (DSPO), an improved RL algorithm designed for robust agent training through sequence-level optimization and dynamic sample filtering. We train our model purely through RL to interleave multi-turn search and reasoning, obviating the need for supervised demonstration data. Across multiple QA benchmarks, our 7B model improves over a comparable previous work by \textbf{34.1\%}, and even outperforms the 14B model from previous work in complex multihop QA such as HotpotQA by nearly \textbf{9\% relative}, maintaining exceptional training stability.

📄 PDF Abstract BibTeX arXiv:2510.09255

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities

2025-08-27 · Rikuto Kotoge, Mai Nishimura, Jiaxin Ma arxiv

Reinforcement Learning has emerged as a dominant post-training approach to elicit agentic RAG behaviors such as search and planning from language models. Despite its success with larger models, applying RL to compact mod…

Reinforcement Learning

RTPO: Reverse-Turn Policy Optimization for Stabilizing Agentic RL Training

2026-08-19 · Yugu Li, Jimmy Cao, Jianglin Qiao, Siyi Hu arxiv

Training multi-turn agentic workflows with reinforcement learning (RL) enables large language models to perform complex reasoning, use external tools, and conduct iterative search beyond single-turn settings. Yet multi-t…

Reinforcement Learning

ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

2026-02-25 · Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi 외 arxiv

Agentic reinforcement learning (ARL) has rapidly gained attention as a promising paradigm for training agents to solve complex, multi-step interactive tasks. Despite encouraging early results, ARL remains highly unstable…

Reinforcement Learning

PaperScout: An Autonomous Agent for Academic Paper Search with Process-Aware Sequence-Level Policy Optimization

2026-01-15 · Tingyue Pan, Jie Ouyang, Mingyue Cheng, Qingchuan Li 외 arxiv

Academic paper search is a fundamental task in scientific research, yet most existing approaches rely on rigid, predefined workflows that struggle with complex, conditional queries. To address this limitation, we propose…

Reinforcement Learning

AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search

2026-01-08 · Zefang Zong, Dingwei Chen, Yang Li, Qi Yi 외 arxiv

LLM agents have emerged as powerful systems for tackling multi-turn tasks by interleaving internal reasoning and external tool interactions. Agentic Reinforcement Learning has recently drawn significant research attentio…

Reinforcement Learning