The paper introduces belief‑shift branching, a method for placing forks in tree‑structured reinforcement learning rollouts by detecting where a model’s answer belief changes most sharply. Unlike traditional fixed‑length or entropy‑based forking, this approach uses a lightweight probe or learned activation direction to identify pivots in the value curve, reducing unnecessary sampling. Experiments show that belief‑shift forking consistently outperforms baseline methods across multiple models and benchmarks, yielding significant gains in mathematics and code tasks.
By Bin Lei, Yu Li, Prafulla Kumar Choubey, Jiaxin Zhang, Becky Xiangyu Peng, Qinyuan Ye, Kartik Narayan, Caiwen Ding, Silvio Savarese, Chien-Sheng Wu
arXiv:2609.01274v1 Announce Type: new
Abstract: Reinforcement learning with verifiable rewards (RLVR) improves language-model reasoning, but how these gains relate to inference-time decoding and sear...
By Wenhe Sun, Cunxiang Wang, Zijun Yao, Yixin Cao
arXiv:2607. 14171v1 Announce Type: new Abstract: Reinforcement learning has emerged as the dominant paradigm for training large language model (LLM) agents that interact with executable sandboxes.
By Bowei He, Yankai Chen, Xiaokun Zhang, Xue Liu
EPIG-Tree proposes a compute‑optimal branching strategy for gradient‑efficient reinforcement learning, arguing that branches should be placed where they most reduce policy‑gradient uncertainty per unit of compute. By deriving allocation laws from a law‑of‑total‑variance decomposition, the method introduces an EPIG‑Tree score that guides branch placement using already computed rollouts, estimating occupancy‑ and score‑weighted value uncertainty. Empirical results show EPIG‑Tree reduces gradient MSE in cloned‑state control, improves frozen‑LLM gradient calibration, and outperforms flat GRPO and entropy branching in both single‑turn math and multi‑turn Wordle tasks.
By Nikita Khomich, Leopold Hermansson, Ido Hakimi
The paper investigates why reinforcement learning with verifiable rewards (RLVR) reduces the diversity of solutions in reasoning tasks. By analyzing the Countdown task, the authors show that RLVR contracts the solution space mainly at the entrance—before the first arithmetic operation—causing a 67% drop in solution coverage. They demonstrate that providing an unselected entrance prefix or applying entrance‑targeted interventions can restore or even improve coverage without harming accuracy.
By Qiancheng Zhou, Ruizhe Li
arXiv:2606. 29476v1 Announce Type: cross Abstract: Self-distilled agentic reinforcement learning augments trajectory-level reward with a token-level distillation loss, using as its teacher the same policy conditioned on privileged context.
By Zibin Meng, Kani Chen
arXiv:2607. 13988v1 Announce Type: new Abstract: Multi-turn agents solve complex tasks through extended sequences of tool interactions before producing a final answer, making credit assignment a fundamental challenge during post-training.
By Leitian Tao, Baolin Peng, Wenlin Yao, Tao Ge, Hao Cheng, Mike Hang Wang, Jianfeng Gao, Sharon Li
arXiv:2609.40035v1 Announce Type: new
Abstract: The policy-gradient theorem gives the exact gradient under the current policy, but finite on-policy samples may miss rare high-return trajectories. We...
By Junyu Lu, Shichao Weng, Zhiqiang Wang, Haojie Luo, Jingfan Zhang, Yuhua Zhou, Cheng Du, Yuzhuo Zhang, Xi Li, Jinwei Du, Tiancheng Feng, Chuan Xiao, Shuyuan Zheng
Contrastive Branch Policy Optimization (CBPO) is a reinforcement learning method that separates the allocation of a fixed rollout budget from the translation of branch outcomes into token-level credit. It uses generation entropy to screen branch positions, path- and node-level decay to distribute the budget, and Contrastive Branch Value (CBV) to estimate local decision sensitivity without changing reward signs. CBPO partitions trajectories into non-overlapping credit segments, preventing duplicated gradients and enabling fine-grained credit assignment using only outcome rewards.
By Ying Wang, Changlin Qiu, Bang Lin, Linbo Jin, Wen Jiang, Zhe Sun, Jingli Yang
arXiv:2606. 25451v1 Announce Type: new Abstract: Estimating token-level advantages in reinforcement learning (RL) for language models remains challenging because scaling up episodic experience collection is expensive.
By Fengdi Che, Yang Liu, Lei Yu, Meng Cao, Tong Che, Rupam Mahmood, Dale Schuurmans
arXiv:2608. 10441v1 Announce Type: new Abstract: Many pipelines can pay a per-example cost to acquire an auxiliary, model-derived observation -- an LLM's structured reasoning, a slow oracle, an expensive measurement -- and then must decide when the acquired signal is worth using.
By Ying Yuan
arXiv:2607. 20543v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) can improve one-sample accuracy while making a model worse under repeated sampling.
By Todd Zhou