1 citations · 1 across the 11 of their papers we have counts for
Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
All Work And No Play Makes Jack a Dull Boy: Understanding and Preventing Catastrophic Strategy Collapse in RLVR
Qiyuan Huang, Tianshi Xu, Meng Li
During post-training of large language models (LLMs) with Reinforcement Learning with Verifiable Rewards (RLVR), GRPO-style algorithms can exhibit severe late-stage collapse. Promp…
cs.LG2026
CLEANER: Self-Purified Trajectories Boost Agentic Reinforcement Learning
Tianshi Xu, Yuteng Chen, Meng Li
Agentic Reinforcement Learning (RL) has empowered Large Language Models (LLMs) to utilize tools like Python interpreters for complex problem-solving. However, for parameter-constra…