paper-with-me

홈 › Papers

SRPO: Self-Reflective Policy Optimization for Long-Horizon Reasoning

2026-08-24 · Jialong Liu, Yuling Shi, Ning Yang, Xiaodong Gu, Zuchao Li arxiv

Self-reflection is a powerful mechanism for credit assignment in human learning, converting sparse outcome feedback into actionable guidance. However, its potential for post-training Large Language Models (LLMs) remains underexplored. We propose Self-Reflective Policy Optimization (SRPO), a framework that internalizes this capability. SRPO enables LLMs to analyze their own completed trajectories, synthesize errors into concise "reflection patches," and use reflection-conditioned teacher scores on student on-policy rollouts as dense token-level training signals. This process effectively transforms sparse terminal supervision into dense, token-level learning signals without requiring external critics, separate reward models, or larger teacher models. We demonstrate that SRPO achieves state-of-the-art performance across mathematical reasoning and long-horizon agentic benchmarks with exceptional data efficiency. Using a Qwen3-8B base model, SRPO attains 73.3% on AIME'24 using only 8% (0.08x) of the training FLOPs required by scaled supervised fine-tuning, while significantly improving success rates on WebShop (64.7%), ALFWorld (76.8%), and SWE-Bench-Lite (31.2%). Code is available at https://github.com/Galleons2029/SRPO

📄 PDF Abstract BibTeX arXiv:2608.23493

Code (0)

등록된 구현이 없습니다.

Tasks

Mathematical Reasoning

Similar Papers 제목 키워드 기반

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

2026-04-02 · Gengsheng Li, Tianyu Yang, Junfeng Fang, Mingyang Song 외 arxiv

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignmen…

Reinforcement Learning

Self-Improving Robust Preference Optimization

2024-06-03 · Eugene Choi, Arash Ahmadian, Matthieu Geist, Oilvier Pietquin 외

Online and offline RLHF methods, such as PPO and DPO, have been highly successful in aligning AI with human preferences. Despite their success, however, these methods suffer from fundamental limitations: (a) Models train…

SRPO: Self-Referential Policy Optimization for Vision-Language-Action Models

2025-11-19 · Senyu Fei, Siyin Wang, Li Ji, Ao Li 외 arxiv

Vision-Language-Action (VLA) models excel in robotic manipulation but are constrained by their heavy reliance on expert demonstrations, leading to demonstration bias and limiting performance. Reinforcement learning (RL) …

Reinforcement Learning

SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning

2025-06-02 · Zhongwei Wan, Zhihao Dou, Che Liu, Yu Zhang 외

Multimodal large language models (MLLMs) have shown promising capabilities in reasoning tasks, yet still struggle with complex problems requiring explicit self-reflection and self-correction, especially compared to their…

Multimodal Reasoningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Credit Assignment with Resets in Language Model Reasoning

2026-05-25 · Ankur Samanta, Akshayaa Magesh, Ayush Jain, Youliang Yu 외 arxiv

Contemporary reinforcement learning with verifiable reward methods post-train language models on multi-step reasoning by assigning a single outcome reward uniformly across all tokens in a trajectory. Such uniform assignm…

Reinforcement Learning