arXiv:2607. 04412v1 Announce Type: new Abstract: Reinforcement learning (RL) for non-verifiable instruction following increasingly relies on LLM judges with prompt-specific rubrics as reward signals.
By Yujin Kim, Namgyu Ho, Sangmin Hwang, Joonkee Kim, Yongjin Yang, Sangmin Bae, Seungone Kim, Jaehun Jung, Se-Young Yun, Hwanjun Song
arXiv:2603.11321v3 Announce Type: replace-cross
Abstract: Reinforcement Learning with Verifiable Rewards improves reasoning in large language models, yet on-policy learning often suffers from cold-st...
By Yuning Wu, Ke Wang, Haoran Liu, Chaoqun Jia, Devin Chen, Kai Wei
arXiv:2601. 03555v3 Announce Type: replace Abstract: Training reliable tool-augmented agents remains a significant challenge, largely due to the difficulty of credit assignment in multi-step reasoning.
By Yuxuan Jiang, Francis Ferraro
SOD: Step-wise On-policy Distillation for Small Language Model Agents proposes a new framework that adaptively reweights distillation strength at each reasoning step based on step-level divergence. This approach mitigates cascading errors in tool-integrated reasoning by attenuating misleading teacher signals in high-divergence regions while preserving dense guidance where student and teacher align. Experiments on math, science, and code benchmarks show up to 20.86% improvement over the second-best baseline, with a 0.6B student scoring 26.13% on AIME 2025.
By Qiyong Zhong, Mao Zheng, Mingyang Song, Xin Lin, Jie Sun, Houcheng Jiang, Xiang Wang, Junfeng Fang
The paper introduces Rollout-Time Intervention (RTI), a method that uses reward-side evidence during rollouts to transform unsuccessful trajectories into successful ones, thereby providing learning signals for tasks beyond a policy’s intrinsic exploration limits. RTI filters out trajectories with excessive distributional shifts, allowing these off-policy interventions to guide policy optimization effectively. Experiments on five benchmarks show that RTI consistently outperforms existing RL baselines, enabling post-trained policies to approach the performance of stronger large language models and surpass their original capability boundaries.
By Chen Xi, Ding Ruixue, Wang Zhigaoyuan, Zhang Fanrui, Zhang Qiang, Chen Boli, Wang Shihang, Wang Tianfu, Ren Ailin, Wang Pengyong, Xie Pengjun, Xiong Hui
CAST is a critique‑aware training framework that transforms sparse task outcomes into action‑level supervision for both critique learning and policy optimization. By analyzing agent trajectories, CAST synthesizes structured rationales that explain action validity under partial observability, enabling the creation of richer training data. Fine‑tuned Qwen3‑family models trained with CAST show significant reliability gains, outperforming GPT‑OSS‑120B by over 10% on Retail tasks and improving Telehealth performance by 9% in an out‑of‑domain setting.
By Amir Saeidi, Zehua Zhang, Rishitosh Singh, Naman Ahuja, Vivek Gupta, Ali Payani, Gaowen Liu, Jayanth Srinivasa, Chitta Baral