多篇研究论文介绍了用于改进代理和多代理系统强化学习（RL）中信用分配的新方法。这些方法旨在更准确地将结果归因于特定决策或行动，尤其是在涉及大型语言模型（LLM）或协作多代理控制的复杂场景中。技术包括可验证可行性表示、分段重加权、近端熵、半事实稳定性以及空间信用分配，在各种基准测试中通常优于现有基线。
AI
arXiv:2609.38889v1 Announce Type: new Abstract: Constrained multi-agent control requires more than predicting rewarding actions: an action can cease to be executable as contact windows, shared capacity, and deadlines change. We introduce VERA, a centralized-training, decentralize…
arXiv cs.AI
TIER_1English(EN)·Xinchen Du, Zhengze Zhou, Wenhui Zhu, Han Yu, Sen Na, Rohit Jain, Alborz Geramifard·
arXiv:2610.00838v1 Announce Type: cross Abstract: Agentic reinforcement learning (RL) trains a large language model (LLM) to act over long, multi-step interactions. However, a single localized error can cause task failure, while trajectory-level rewards provide limited guidance f…
arXiv cs.AI
TIER_1English(EN)·Yun Kim, Nojun Kwak·
arXiv:2609.39402v1 Announce Type: new Abstract: Value-model-free RLVR methods such as GRPO assign uniform advantages to all tokens in a rollout, ignoring that tokens contribute unequally. Recent methods use token entropy as an importance proxy but compute it globally across the b…
arXiv:2609.40360v1 Announce Type: cross Abstract: Reinforcement learning with verifiable rewards (RLVR) has improved the reasoning capabilities of large language models (LLMs), yet their predictions remain sensitive to task-irrelevant prompt features. We investigate this sensitiv…
arXiv:2609.36178v1 Announce Type: cross Abstract: Group Relative Policy Optimization (GRPO) has become a promising approach for training large language model agents. However, its uniform assignment of trajectory-level advantages to all policy tokens fails to distinguish consequen…
arXiv:2609.36505v1 Announce Type: new Abstract: Agentic reinforcement learning (ARL) with verifiable rewards improves the ability of large language models (LLMs) to tackle knowledge-intensive tasks by learning to interleave search and reasoning. However, most existing ARL methods…
arXiv:2609.36572v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) has been extended to Large Vision-Language Models (LVLMs), and perception-aware methods further encourage policies to rely on visual evidence. Yet relying on the image does not g…
arXiv cs.AI
TIER_1English(EN)·Shengtian Yang, Ziyu Xiong, Kaibing Yang, Guangfeng Cai, Yewen Li, Peng Jiang, Gai Kun, Qingpeng Cai, Lei Feng·
arXiv:2609.36939v1 Announce Type: new Abstract: GUI agents automate tasks on digital devices by grounding language instructions in visual interfaces. Existing group-relative reinforcement learning improves GUI action prediction by comparing the rewards of multiple responses sampl…
arXiv:2609.31531v1 Announce Type: new Abstract: Cooperative multi-agent reinforcement learning under partial observability and shared rewards requires assigning team outcomes to individual agents and high-order coalitions. A MAPPO-style critic compresses joint behavior into one g…
