Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
RSIGym: A Flexible Environment for Recursive Self-Improvement
Fanqing Meng, Lingxiao Du, Haocheng Lu +6
Recursive self-improvement requires carrying accepted changes into later improvement cycles, while studying agent-proposed changes also requires substantial research infrastructure…
cs.LG2025
CPGD: Toward Stable Rule-based Reinforcement Learning for Language Models
Zongkai Liu, Fanqing Meng, Lingxiao Du +4
Recent advances in rule-based reinforcement learning (RL) have significantly improved the reasoning capability of language models (LMs) with rule-based rewards. However, existing R…