Group Relative Policy Optimization (GRPO) assigns a magnitude to each rollout based on within‑group reward statistics, rewarding rollouts that reach the correct answer through reasoning. However, the same magnitude can be high for rollouts that reach the answer by guessing, creating a spurious advantage that misleads the policy toward guess‑like behaviors. The paper identifies three scenarios where this occurs—bounded‑answer tasks, open‑answer sets with bounded sub‑cases, and search agents with many paths to the same answer—and proposes SIGNBALANCE, a composition‑free magnitude that preserves the verifier sign, uses a global scale, and restores zero‑mean balance via stop‑gradient per‑class rescaling, matching GRPO on open‑answer math and improving on bounded‑answer math and search agents.
By Jiamian Wang, Samyadeep Basu, Koustava Goswami, Tong Yu, Zhiqiang Tao
arXiv:2610.09804v1 Announce Type: new
Abstract: Reinforcement learning is now central to eliciting reasoning in large language models, while in the popular algorithm Group Relative Policy Optimizatio...
By Yingxiang Yang, Weihang Xiao, Zhunxuan Wang, Joshua Flashner, Niresh Agarwal
The paper introduces Grounded Credit Assignment (GCA) for reinforcement learning in multi‑turn search agents. GCA separates credit for evidence retrieval and answer correctness, correcting the bias in GRPO that favors evidence‑retrieving rollouts only proportionally to accuracy gains. Applying GCA to Search‑R1 boosts average EM by 5.7–6.3 points and increases the proportion of evidence‑supported correct answers from 76.9% to 93.4%.
By Qirui Liu, Hao Chen, Yi Wen, Weijie Shi, Yao Zhao, Xianhe Chen, Hao Zhao, Xing Tang, Weihong Luo, Yuyu Luo
The paper introduces APIVIS, a training-time framework that integrates finite-budget Gumbel search into reinforcement learning with verifiable rewards (RLVR) for mathematical reasoning. APIVIS combines direct and searched responses within each rollout group, uses selective supervision on search-improved tokens, and applies value-guided selection to improve verifier rewards at each searched state. Experiments on standard mathematical reasoning benchmarks and various model scales show significant performance gains over existing search-based methods.
By Shaohuai Liu, Yuning Wu, Haoran Liu, Enzo Jia, Devin Chen, Kai Wei
arXiv:2608. 03119v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) improves LLM reasoning but typically relies on ground-truth (GT) answers, limiting scalability.
By Yongshi Ye, Liang Zhang, Yidong Chen, Xiaodong Shi, Biao Fu
arXiv:2604.18235v3 Announce Type: replace-cross
Abstract: Search agents achieve strong question-answering performance through multi-turn interactions with search engines, with Group Relative Policy O...
By Jiayi Wu, Ruobing Xie, Zeqian Huang, Lei Jiang, Can Xu, Kangyang Luo, Bochen Lin, Ming Gao, Xiang Li