paper-with-me

홈 › Papers

SeRL: Self-Play Reinforcement Learning for Large Language Models with Limited Data

2025-05-25 · Wenkai Fang, Shunyu Liu, Yang Zhou, Kongcheng Zhang, Tongya Zheng, KaiXuan Chen, Mingli Song, DaCheng Tao

Recent advances have demonstrated the effectiveness of Reinforcement Learning (RL) in improving the reasoning capabilities of Large Language Models (LLMs). However, existing works inevitably rely on high-quality instructions and verifiable rewards for effective training, both of which are often difficult to obtain in specialized domains. In this paper, we propose Self-play Reinforcement Learning(SeRL) to bootstrap LLM training with limited initial data. Specifically, SeRL comprises two complementary modules: self-instruction and self-rewarding. The former module generates additional instructions based on the available data at each training step, employing robust online filtering strategies to ensure instruction quality, diversity, and difficulty. The latter module introduces a simple yet effective majority-voting mechanism to estimate response rewards for additional instructions, eliminating the need for external annotations. Finally, SeRL performs conventional RL based on the generated data, facilitating iterative self-play learning. Extensive experiments on various reasoning benchmarks and across different LLM backbones demonstrate that the proposed SeRL yields results superior to its counterparts and achieves performance on par with those obtained by high-quality data with verifiable rewards. Our code is available at https://github.com/wantbook-book/SeRL.

📄 PDF Abstract BibTeX arXiv:2505.20347

Code (1)

wantbook-book/serl 공식 구현 pytorch

Tasks

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

SERL: Self-Examining Reinforcement Learning on Open-Domain

2025-11-11 · Weixuan Ou, Yanzhao Zheng, Shuoshuo Sun, Wei Zhang 외 arxiv

Reinforcement Learning (RL) has been shown to improve the capabilities of large language models (LLMs). However, applying RL to open-domain tasks faces two key challenges: (1) the inherent subjectivity of these tasks pre…

Reinforcement Learning

DenoiseRL: Bootstrapping Reasoning Models to Recover from Noisy Prefixes

2026-05-27 · Caijun Xu, Changyi Xiao, Zhongyuan Peng, Yixin Cao arxiv

Reinforcement learning has become a central paradigm for advancing reasoning in large language models, yet most existing methods still depend on stronger teacher models or heavily curated difficult datasets, limiting sca…

Reinforcement Learning

Skill Reuse as Compression in Agentic RL

2026-05-29 · Zhikun Xu, Yu Feng, Jacob Dineen, Taiwei Shi 외 arxiv

Large language model agents trained with reinforcement learning (RL) often learn brittle, task-specific shortcuts. We hypothesize that agents generalize better when their successful trajectories are structurally compress…

Reinforcement Learning

Learning from Ambiguous Demonstrations with Self-Explanation Guided Reinforcement Learning

2021-10-11 · Yantian Zha, Lin Guan, Subbarao Kambhampati

Our work aims at efficiently leveraging ambiguous demonstrations for the training of a reinforcement learning (RL) agent. An ambiguous demonstration can usually be interpreted in multiple ways, which severely hinders the…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)

SERL-SQL: Selective Hindsight Distillation for Text-to-SQL Reinforcement Agentic Learning

2026-08-01 · Tao Liu, Tao Feng, Xiangheng Li, Jinwang Song 외 arxiv

Recent Text-to-SQL systems increasingly rely on multi-turn interaction, execution feedback, and reinforcement learning. However, most existing methods use execution correctness only as a trajectory-level reward, which pr…

Reinforcement Learning