paper-with-me

Papers

Learning Agentic Policy from Action Guidance

2026-05-12 · Yuxiang Ji, Zengbin Wang, Yong Wang, Shidong Yang, Ziyu Ma, Guanhua Chen, Zonghua Sun, Liaoni Wu, Xiangxiang Chu arxiv

Agentic reinforcement learning (RL) for Large Language Models (LLMs) critically depends on the exploration capability of the base policy, as training signals emerge only within its in-capability region. For tasks where the base policy cannot reach reward states, additional training or external guidance is needed to recover effective learning signals. Rather than relying on costly iterative supervised fine tuning (SFT), we exploit the abundant action data generated in everyday human interactions. We propose \textsc{ActGuide-RL}, which injects action data as plan-style reference guidance, enabling the agentic policy to overcome reachability barriers to reward states. Guided and unguided rollouts are then jointly optimized via mixed-policy training, internalizing the exploration gains back into the unguided policy. Motivated by a theoretical and empirical analysis of the benefit-risk trade-off, we adopt a minimal intervention principle that invokes guidance only as an adaptive fallback, matching task difficulty while minimizing off-policy risk. On search-agent benchmarks, \textsc{ActGuide-RL} substantially improves over zero RL (+10.7 pp on GAIA and +19 pp on XBench with Qwen3-4B), and performs on par with the SFT+RL pipeline without any cold start. This suggests a new paradigm for agentic RL that reduces the reliance on heavy SFT data by using scalable action guidance instead.

📄 PDF Abstract BibTeX arXiv:2605.12004

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering

2026-05-28 · Xin Sun, Jianan Xie, Zhongqi Chen, Qiang Liu 외 arxiv

Reinforcement learning (RL) is a natural fit for agentic knowledge base question answering (KBQA), where a model must issue executable actions, observe knowledge-base feedback, and eventually return an answer. However, c…

Knowledge Base Question AnsweringReinforcement Learning

Group-Reflective Self-Distillation for Agentic Reinforcement Learning

2026-07-30 · Binbin Zheng, Zijun Xie, Guanqun Zhao, Enlei Gong 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) is effective for training large language model agents. However, terminal rewards provide only coarse trajectory-level supervision, leaving successful behaviors, recur…

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

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

Dynamic Dual-Granularity Skill Bank for Agentic RL

2026-03-30 · Songjun Tu, Chengdong Xu, Qichao Zhang, Yaocheng Zhang 외 arxiv

Agentic RL can benefit substantially from reusable experience, yet existing skill-based methods mainly extract trajectory-level guidance and often lack principled mechanisms for maintaining an evolving skill memory. We p…