paper-with-me

Papers

RTMC: Step-Level Credit Assignment via Rollout Trees

2026-04-13 · Tao Wang, Suhang Zheng, Xiaoxiao Xu arxiv

Multi-step agentic reinforcement learning benefits from fine-grained credit assignment, yet existing approaches offer limited options: critic-free methods like GRPO assign a uniform advantage to every action in a trajectory, while learned value networks introduce notable overhead and can be fragile under sparse rewards. We observe that group rollouts targeting the same problem often traverse overlapping intermediate states, implicitly forming a tree whose branches diverge at successive decision points. Building on this insight, we introduce Rollout-Tree Monte Carlo (RTMC) advantage estimation, which aggregates return statistics across rollouts sharing a common state to produce per-step Q-values and advantages--without any learned critic. A state-action signature system compresses raw interaction histories into compact, comparable representations, making cross-rollout state matching tractable. On SWE-bench Verified, RTMC improves pass@1 by 3.2 percentage points over GRPO.

📄 PDF Abstract BibTeX arXiv:2604.11037

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

On the Policy Gradient Foundations of Group Relative Policy Optimization: Credit Assignment, Gradient Sparsity, and Rank Collapse

2026-06-28 · Amritansh Mishra, Supriyo Chakraborty, Berkcan Kapusuzoglu arxiv

Group Relative Policy Optimization (GRPO) eliminates the learned critic in PPO by using the mean reward of grouped rollouts as a baseline. We provide a rigorous derivation of GRPO from first principles of the policy grad…

Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning

2026-05-26 · Xin Cheng, Shuo He, Lang Feng, HaiYang Xu 외 arxiv

Group-based reinforcement learning (RL) methods have achieved remarkable success in improving the performance of large language models (LLMs) and have been rapidly extended to agentic tasks. However, their credit assignm…

Reinforcement Learning

Learning from the Irrecoverable: Error-Localized Policy Optimization for Tool-Integrated LLM Reasoning

2026-02-10 · Qiao Liang, Yuke Zhu, Chao Ge, Lei Yang 외 arxiv

Tool-integrated reasoning (TIR) enables LLM agents to solve tasks through planning, tool use, and iterative revision, but outcome-only reinforcement learning in this setting suffers from sparse, delayed rewards and weak …

Reinforcement Learning

MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue

2026-03-06 · Naifan Zhang, Ruihan Sun, Jinwei Su, Hengjie Yang 외 arxiv

Reinforcement learning (RL) for large language models (LLMs) has shown strong performance in single-turn tasks, but extending it to multi-turn interaction remains challenging due to sparse rewards and poor per-turn credi…

Reinforcement Learning

Element-Aware Group Learning for E-Commerce Image Generation

2026-08-01 · Jingtong Chen, Jiahui Wang, Xue Zhao, ShaoGuo Liu 외 arxiv

Recent advances in image generation and editing have made prompt quality a key bottleneck for e-commerce creatives. Vision-language models (VLMs) can generate image-editing prompts from product images and metadata, but f…

Image Generation