跳到正文
HuggingFace Daily Papers(社區熱門論文)·· 2026-10-11AI 評分38

RSIPO:透過技能與策略共同演化,實現智能體強化學習的遞迴自我改進策略最佳化

RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution

AI 導讀

RSIPO 是一種自我演化的智能體強化學習框架,讓智能體技能與策略模型在訓練過程中共同演化。它從已完成的軌跡中提取技能,並以經驗貝葉斯收縮方法校準對教師評分的信任度。以千問 Qwen2.5-7B 為基礎模型時,RSIPO 在 ALFWorld 的平均成功率達 98.6%,較次佳基線及標準 GRPO 分別絕對提升 2.5% 和 17.4%。

正文

Published on Oct 11

Authors:

,

,

,

,

,

,

,

,

Abstract

Recent focus in agentic reinforcement learning (RL) seeks to improve credit assignment in long-horizon tasks. One promising direction combines reinforcement learning with verifiable rewards (RLVR) and on-policy self-distillation (OPSD), integrating trajectory-level advantages with dense token-level supervision. This line of work often conditions a teacher model on privileged context, such as agentic skills, to score tokens generated by the student policy. Despite their progress, they largely overlook the on-policy evolution of agentic skills and the reliability of teacher supervision. Towards this end, we introduce Recursive Self-Improving Policy Optimization (RSIPO), a self-evolving agentic RL framework that enables agentic skills and the policy model to co-evolve throughout the training process. Specifically, RSIPO enables the policy itself to extract skills from completed trajectories and explicitly optimizes its skill-generation capability through trajectory replay. It further employs empirical Bayes shrinkage to dynamically calibrate the student's trust in teacher scores, accounting for the fact that skill-enhanced teacher guidance can sometimes be less reliable. Experiments with Qwen-family models on embodied interaction and search-based agentic tasks demonstrate that RSIPO outperforms all the compared baseline approaches. With Qwen2.5-7B as the base model, RSIPO achieves an average success rate of 98.6\% on ALFWorld, yielding absolute improvements of 2.5\% and 17.4\% over the second-best baseline and standard GRPO, respectively.

View arXiv page View PDF GitHub Add to collection

Get this paper in your agent:

hf papers read 2610.15772

Don't have the latest CLI?

curl -LsSf https://hf.co/cli/install.sh | bash

Models citing this paper 0

No model linking this paper

Cite arxiv.org/abs/2610.15772 in a model README.md to link it from this page.

Datasets citing this paper 0

No dataset linking this paper

Cite arxiv.org/abs/2610.15772 in a dataset README.md to link it from this page.

Spaces citing this paper 0

No Space linking this paper

Cite arxiv.org/abs/2610.15772 in a Space README.md to link it from this page.

Collections including this paper 0

No Collection including this paper

Add this paper to a collection to link it from this page.

來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co