Overview

Credit assignment asks which decisions or components contributed to a success or failure, so learning can reinforce useful behavior and correct mistakes. Common approaches estimate counterfactual or marginal contributions, trace dependencies through interaction graphs, or localize rewards to steps, segments, tokens, or spatial regions. These methods are used in cooperative reinforcement learning, multi-turn LLM and tool-using agents, embodied control, and neural learning, with evaluations ranging from task success and reasoning benchmarks to attribution accuracy. The central tension is that finer-grained signals can improve learning but are costly or noisy, while dense intermediate rewards may misdirect updates when they do not reliably reflect causal contribution.

Latest papers

CardsList

75 papers11 papers in the last four weeks, down 42% on the four weeks before. 0.1% of all new papers.

  1. When Credit Turns Against Tools: Transition-Aware Credit Assignment in Agentic Reinforcement Learning

    Nov 8, 2026Xiangyu Lu, Zhanke Zhou, Jiazhe Ning +3Agentic RLCredit Assignment

  2. Catalyzing Interactive HTML Generation Capabilities via High-Fidelity Reinforcement Learning

    Nov 3, 2026Xujia Wang, Yixuan Liu, Shaohan Huang +4RL for Code GenerationReinforcement Learning

  3. Learning from Relative Action Credit for Escaping Local Minima

    Oct 27, 2026Giovanni Minelli, Giulio Turrisi, Lorenzo Amatucci +2Reinforcement LearningRobotic RL

  4. LoCA: Local Credit Assignment for Reinforcement Learning of Autoregressive Flow-Matching TTS

    Oct 20, 2026Jie Liu, Junyu Zhou, Junhao Zhong +5TTS SynthesisCredit Assignment

  5. WEAVE: Weaving Real-World Code Evolution into Dependency-Structured Tasks for Benchmarking and Training Code Agents

    Oct 15, 2026Weihao Li, Zihang Xu, Zhongqiu Wang +7Software Engineering BenchmarksSoftware Engineering Agents

  6. Blame Errant Words, Not the Canvas: Defect-Aware Spatial Credit Assignment for Visual Text Generation

    Oct 14, 2026Sujie Hu, Huaisong Zhang, Pujing Yang +7Text Rendering in T2I GenerationReward Modeling

  7. MAS-Gate: Unlocking Multi-Agent System Lifecycle via Node-Centric Quantification

    Oct 13, 2026Hehai Lin, Zixuan Wang, Ming Yan +6LLM Agent Workflow OptimizationMulti-Agent Orchestration

  8. RAP-WAM: Learning World-Action Models through Predictive Rehearsal and Action Perturbations

    Oct 12, 2026Yuanpeng He, Ceyao Zhang, Fangjing Li +8Visuomotor Policy LearningWorld Action Models

  9. Of Errors and Echoes: Responsibility-Aware Credit Assignment for Tool-Use Agents

    Oct 12, 2026Xingjian Diao, Tianyu Yang, Wenjun Huang +8Credit AssignmentFine-Grained Credit Assignment

  10. Learning after Execution with Action-Specific Credit

    Oct 10, 2026Yufeng Tian, Jiahao Tang, Minghao WuReinforcement LearningCredit Assignment

  11. MemTrial: Learning When to Trust Memory in LLM Portfolio Agents

    Oct 8, 2026Guanghao Wu, Zhuo Cai, Shoujin WangLLM Agent MemoryCredit Assignment

  12. GraphOPD: Graph-Augmented On-Policy Distillation for LLM Agents

    Oct 6, 2026Bohan Lin, Liyi Chen, Zhuoning Guo +5LLM Agent TrainingOn-Policy Distillation

  13. Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents

    Oct 2, 2026Yu Li, Guangfeng Cai, Long-Fei Li +5Credit AssignmentStep-Level Credit Assignment in RL

  14. My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning

    Oct 1, 2026Yihua Zhu, Qianying Liu, Weixu Qiao +10Agentic RLCredit Assignment in RL

  15. SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning

    Sep 30, 2026Xinchen Du, Zhengze Zhou, Wenhui Zhu +4Agentic RLGroup Relative Policy Optimization

  16. PRICE the Action Chunks: Physical Relational Credit Assignment for Embodied Reinforcement Learning

    Sep 30, 2026Yangang Zou, Jiajun Lu, Weitao Zhou +6Credit Assignment in RLStep-Level Credit Assignment in RL

  17. VERA: Verifiable Feasibility Representations with Counterfactual Credit for Constrained Multi-Agent Control

    Sep 30, 2026Bo Yin, Dongbo Li, Hongkai Chen +2Multi-Agent ControlConstrained RL

  18. Credit-Guided Policy Improvement for Test-time Adaptive Vision-Language Navigation

    Sep 29, 2026Yang Li, Sijia Zhang, Yihan Li +4Robot Policy LearningRobot Policy Adaptation

  19. SCA: Spatial Credit Assignment for Reinforcement Learning of GUI Agents

    Sep 29, 2026Shengtian Yang, Ziyu Xiong, Kaibing Yang +6Reinforcement LearningRL for GUI Agents

  20. Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning

    Sep 28, 2026Dongwon Jung, Hemanth Neelgund Ramesh, Yifan Wang +7Agentic RLGroup Relative Policy Optimization

  21. Dr.Credit: Rubric-Grounded Process Credit Assignment for Deep Research Agents

    Sep 28, 2026Yingjian Zhu, Zhenyi Wang, Jiaxin Guo +6Deep Research AgentsStep-Level Credit Assignment in RL

  22. SGA-Flow-GRPO: Spatial Gradient-Guided Credit Assignment for Flow-GRPO

    Sep 26, 2026Yunkai Yang, Yudong Zhang, Xinying Chen +5Diffusion Model AlignmentRL for Diffusion Models

  23. From Interests to Semantic IDs: Retrieval-Grounded Credit Assignment for Generative Recommendation

    Sep 24, 2026Mengdan Zhu, Yufan Zhao, Yao Zhao +5Semantic ID RecommendationCredit Assignment

  24. SLCA-GRPO: Resolving Cross-Segment Credit Misattribution in Tool-Calling RL

    Sep 24, 2026Yan Zhan, Shaobo Liu, Qiunan Liu +7Group Relative Policy OptimizationCredit Assignment in RL

  25. When Does Action Credit Need Updating?

    Sep 24, 2026Hongye Yang, Boxiao HuangCredit Assignment in RLCredit Assignment