Group Adaptive Clipping Policy Optimization (GAPO) is a plug‑in modification to GRPO methods that adapts the importance‑sampling clipping boundary based on rollout advantage. By allowing rollouts with larger learning signals to receive proportionally greater update headroom, GAPO addresses the limitation of fixed clipping that suppresses rare but informative rollouts. Experiments on Qwen and Llama models show that GAPO consistently improves Pass@1 and Pass@k on math reasoning and coding benchmarks where base model pass rates are low.
By Sheng Jia, Xiao Wang, Shiva Prasad Kasiviswanathan, Rein Houthooft
arXiv:2602. 04879v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has become a cornerstone for fine-tuning Large Language Models (LLMs), with Proximal Policy Optimization (PPO) serving as the de facto standard algorithm.
By Penghui Qi, Xiangxin Zhou, Zichen Liu, Tianyu Pang, Chao Du, Min Lin, Wee Sun Lee
arXiv:2606. 03382v1 Announce Type: cross Abstract: While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments.
By Bingxu Liu, Jiashun Liu, Johan Obando-Ceron, Hao Wang, Runze Liu, Pablo Samuel Castro, Aaron Courville, Ling Pan
While Proximal Policy Optimization (PPO) demonstrates strong performance in stationary settings, we show that its standard optimization paradigm struggles in continual and non-stationary environments. The failure does not stem from insufficient model capacity or overly restrictive clipping.
arXiv:2606. 10968v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has become standard for improving LLM reasoning.
By Renjie Mao, Xiangxin Zhou, Lvfang Tao, Yixin Ding, Yu Shi, Yongguang Lin, Yuheng Wu, Honglin Zhu, Qian Qiu, Wenxi Zhu
arXiv:2602.05863v3 Announce Type: replace
Abstract: Group Relative Policy Optimization (GRPO) remains the dominant critic-free approach for fine-tuning LLMs and VLMs, but its compatibility with const...
By Roger Girgis, Rodrigue de Schaetzen, Luke Rowe, Azal\'ee Robitaille, Christopher Pal, Liam Paull
arXiv:2606. 16154v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but GRPO-style optimization remains prone to collapse.
By Prasanth YSS, Zhichen Ren, Rasa Hosseinzadeh, Ilan Gofman, Yuqi Chen, Zhaoyan Liu, Guangwei Yu, Jesse C. Cresswell, Satya Krishna Gorti
The paper introduces Entropy‑Normalized Trust Region (ENTR), a method for asynchronous reinforcement learning that adjusts off‑policy ratio thresholds based on token entropy rather than a single magnitude cut‑off. By recognizing that the natural scale of the ratio is set by entropy, ENTR preserves genuine exploration while filtering out noise from low‑entropy, stale data. Experiments on long‑horizon agentic tasks and mathematical reasoning benchmarks show ENTR outperforms existing asynchronous methods, improving BrowseComp‑Plus performance by 6.9 % and enabling stable training up to 30 policy versions of staleness while matching synchronous GRPO at a 2.6× speedup.
By Guanqun Zhao, Zijun Xie, Binbin Zheng, Yehan Yang, Jiafeng Lu, Aoqi Hu, Enlei Gong, Zeyu Chen
arXiv:2606. 10228v1 Announce Type: cross Abstract: Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains.
By Kaustubh Mani, Yann Pequignot, Vincent Mai, Liam Paull
arXiv:2606. 25526v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning assumes each agent shares the same reward function and can be trained effectively using the Trust Region framework of single-agent.
By Bang Giang Le, Viet Cuong Ta
The paper introduces Trust Region Q Adjoint Matching (TRQAM), an off‑policy fine‑tuning algorithm that stabilizes reinforcement learning of pretrained flow policies by adaptively controlling the path‑space KL divergence between the fine‑tuned and pretrained policies. TRQAM achieves this through projected dual descent, which adjusts a trust‑region parameter λ during sampling and ensures the KL penalty is exactly weighted in the stochastic optimal control objective. Experiments on 50 OGBench tasks show TRQAM consistently outperforms prior methods, achieving a 68% success rate in offline RL versus 46% for the strongest baseline.
By Yonghoon Dong, Kyungmin Lee, Changyeon Kim, Jaehyuk Kim, Jinwoo Shin
arXiv:2606. 09821v1 Announce Type: new Abstract: Reinforcement learning (RL) has become a key component of post-training large language models (LLMs).
By Jiarui Yao, Xiangxin Zhou, Penghui Qi, Wee Sun Lee, Liefeng Bo, Tianyu Pang