Credit Assignment

Ask about this topic

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

71 papers24 papers in the last four weeks, up 200% on the four weeks before. 0.1% of all new papers.

  1. In-Context Credit Assignment via the Core

    May 7, 2026Keegan Harris, Siddharth Prasad, Asher TrockmanCooperative Game TheoryCredit Assignment

    UC Berkeley · Toyota Technological Institute at Chicago · Google Research

  2. Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers

    May 6, 2026Senkang Hu, Yong Dai, Xudong Han +4Agentic RLReinforcement Learning

    Hong Kong JC STEM Lab of Smart City · City University of Hong Kong · University of Oxford +4

  3. Tree-based Credit Assignment for Multi-Agent Memory System

    May 6, 2026Marina Mao, Alexandr Liu, Pengbo Li +3Credit AssignmentLong-Horizon LLM Agents

    University of Science and Technology of China · 2LLM Department, Tencent · 3The Hong Kong University of Science and Technology +1

  4. Hidden States Know Where Reasoning Diverges: Credit Assignment via Span-Level Wasserstein Distance

    Apr 25, 2026Xinzhu Chen, Wei He, Huichuan Fan +7Token-Level Credit AssignmentGroup Relative Policy Optimization

    Beijing University of Posts and Telecommunications · Meituan · Tianjin University +3

  5. Reducing Credit Assignment Variance via Counterfactual Reasoning Paths

    Apr 20, 2026Fei Ding, Yongkang Zhang, Youwei Wang +1RL for Language Model ReasoningCredit Assignment in RL

    Alibaba Group · Tsinghua University

  6. COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams

    Apr 20, 2026Shripad Deshmukh, Jayakumar Subramanian, Raghavendra Addanki +1Sequential MARLCredit Assignment in RL

    College of Information and Computer Sciences University of Massachusetts Amherst · Adobe Research San Jose, CA

  7. Where Hindsight Credit Can Reside: A Signed-Capacity View of Token Updates in RLVR

    Apr 13, 2026Yuhang He, Haodong Wu, Siyi Liu +7RL for Language Model ReasoningToken-Level Credit Assignment

    The Hong Kong University of Science and Technology (Guangzhou) · Huawei Technologies Ltd.

  8. Marginal-Contribution Policy Gradients under Filtered Feedback for Multi-Agent LLMs

    Apr 3, 2026Elai Ben-Gal, Stela TongMulti-Agent LLM SystemsMulti-Agent System Optimization

    Department of Mathematics Stanford University · Graduate School of Business Stanford University

  9. Execution-Grounded Credit Assignment for GRPO in Code Generation

    Mar 17, 2026Abhijit Kumar, Natalya Kumar, Shikhar GuptaRL for Code GenerationCredit Assignment

  10. The Trace Is the State: Exact Credit Assignment for LLM Agent Teams

    Mar 6, 2026Yanjun Chen, Yirong Sun, Hanlin Wang +5Credit AssignmentCounterfactual Credit Assignment

    Eastern Institute of Technology · The Hong Kong Polytechnic University · Harbin Institute of Technology

  11. Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning

    Jan 29, 2026Bang Giang Le, Viet Cuong TaCredit Assignment in RLCredit Assignment

    Human-Machine Interaction Laboratory VNU University of Engineering and Technology, Hanoi, Vietnam