Credit Assignment in RL

RL: Reinforcement Learning

Follow this topic Ask about this topic

Momentum

32 papers in the last four weeks, up 220% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28

Latest papers 171

All topics

EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents
Aug 2, 2026Jianan Xie, Xin Sun, Zhongqi Chen +4Agentic Search Credit Assignment in RL
ShanghaiTech University · NLPR, MAIS, CASIA · Ant Group
BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent
Aug 2, 2026Yibin Huang, Bin Xu, Hailong Cao +1Process Reward Models Credit Assignment in RL
Faculty of Computing, Harbin Institute of Technology
Gated Q-learning: Add Off-Policy Bias to Taste
Jul 31, 2026Brett DaleyCredit Assignment in RL Step-Level Credit Assignment in RL
Meta
Group-Reflective Self-Distillation for Agentic Reinforcement Learning
Jul 30, 2026Binbin Zheng, Zijun Xie, Guanqun Zhao +4Agentic RL Credit Assignment in RL
University of Science and Technology of China · 2Baidu Inc. · 3Peking University +3
MARS-RA: Rank Aggregation for Credit Assignment via Multimodal Comparisons in Embodied Multi-Agent Cooperation
Jul 30, 2026Dawei Wang, Di Zhao, Xinyuan Liu +5Credit Assignment in RL Cooperative MARL
Newcastle University, United Kingdom · University of Auckland, New Zealand
Harness-G: A Graph-Structured Harness for Search Agents
Jul 30, 2026Yanning Hou, Haoyuan Chen, Sihang Zhou +7Graph Retrieval-Augmented Generation Credit Assignment in RL
National University of Defense Technology · Changsha, China
ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning
Jul 30, 2026Zhenrong Zhang, Fei Wu, Jun Du +2RL for Language Model Reasoning Credit Assignment in RL
1IFLYTEK Research · University of Science and Technology of China
DHRCL:Training Code LLMs with Dense Hierarchical Rewards and Curriculum Learning
Jul 29, 2026Shuhang Wang, Ziming Li, Hui ChengRL for Code Generation Reinforcement Learning
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
Jul 28, 2026Yu Wang, Yi-Kai Zhang, Wentao Shi +8Reinforcement Learning Game-Playing Agents
University of Science and Technology of China · 4Meituan, China · 2Nanjing University +1
Outcome-Confounded Local Supervision in On-Policy Distillation
Jul 26, 2026Guoqing MaCredit Assignment in RL Language Model Distillation
The Chinese University of Hong Kong, Shenzhen
Rewarding Better Thinking for LLM Preference Alignment
Jul 22, 2026Xubo Liu, Wenya Guo, Ruxue Yan +2Process Reward Models Credit Assignment in RL
VCIP, DISSec, College of Computer Science, Nankai University, Tianjin, China
CriPO: Enhancing Rubric-based RL via Self-Distillation
Jul 20, 2026Mingxuan Xia, Yuhang Yang, Chao Ye +7Credit Assignment in RL Rubric-Based RL
Zhejiang University · ByteDance
Decentralized Multi-agent Reinforcement Learning for Resilient Critical Infrastructures
Jul 20, 2026Minghui Ding, Evangelos PournarasMulti-Agent Coordination Credit Assignment in RL
School of Computer Science, University of Leeds, Leeds, UK
Counterfactual Shapley Credit Assignment
Jul 18, 2026Mingxuan Li, Kai-Zhan Lee, Elias BareinboimCredit Assignment in RL Temporal Credit Assignment
Department of Computer Science, Columbia University, New York, NY, USA
Feedback Attribution and Representation Geometry: Metrics for Comparing Individual and Shared Rewards in MARL
Jul 17, 2026Tasha Pais, Richard HigginsCredit Assignment in RL Cooperative MARL
Softmax, San Francisco, CA, USA.
TRACE: Turn-level Reward Assignment via Credit Estimation for Long-Horizon Agents
Jul 15, 2026Leitian Tao, Baolin Peng, Wenlin Yao +5Credit Assignment in RL Step-Level Credit Assignment in RL
University of Wisconsin–Madison · Microsoft Research
When Implausible Tokens Get Reinforced: Tail-Aware Credit Calibration for LLM Reinforcement Learning
Jul 8, 2026Xiuyi Lou, Zicheng Xu, Yu-Neng Chuang +4RL for Language Models Token-Level Credit Assignment
Johns Hopkins University · Rice University · Workato +1
Agent Reinforcement Learning via Pivotal-Aware Self-Feedback Retry
Jul 4, 2026Weiyang Guo, Zesheng Shi, Longhui Zhang +3Reinforcement Learning Credit Assignment in RL
Harbin Institute of Technology, Shenzhen, China
Diffusing Blame: Task-Dependent Credit Assignment in Biologically Plausible Dual-Stream Networks
Jun 30, 2026Yutaro Yamada, Luca Grillotti, Rujikorn Charakorn +3Credit Assignment in RL Biologically Plausible Learning
Sakana AI
ECHO: Prune To Act, Trace To Learn With Selective Turn Memory In Agentic RL
Jun 30, 2026Zijun Xie, Binbin Zheng, Enlei Gong +7Agentic RL Credit Assignment in RL
School of Mathematical Sciences, Peking University · Baidu Inc. · University of Science and Technology of China
Toward an Energy-Optimized Operation of Data Centers Located in Wind Farms Using Reinforcement Learning
Jun 29, 2026Jan Stenner, Alexander Kilian, Sebastian Peitz +1RL Control Credit Assignment in RL
Software Innovation Campus Paderborn, Paderborn University, Germany · Chair of Computer Networks and Computer Communications, University of Passau, Germany · Lamarr Institute for Machine Learning and Artificial Intelligence, Technical University of Dortmund, Germany
From Detecting Agency to Doing Work: Self-Caused Credit Builds a Durable Behavioral Self in a Minimal Spiking Agent
Jun 29, 2026Haoliang HanCredit Assignment in RL Credit Assignment
Institute of Biomedical Strategy, China Pharmaceutical University
ECHO: Learning Epistemically Adaptive Language Agents with Turn-Level Credit
Jun 29, 2026Abhijnan Nath, Nikhil KrishnaswamyBelief-Space Planning Credit Assignment in RL
Situated Grounding and Natural Language (SIGNAL) Lab Department of Computer Science, Colorado State University Fort Collins, CO 80523 USA
UCOB: Learning to Utilize and Evolve Agentic Skills via Credit-Aware On-Policy Bidirectional Self-Distillation
Jun 28, 2026Songjun Tu, Chengdong Xu, Qichao Zhang +6Credit Assignment in RL LLM Agent Skill Learning
Institute of Automation, Chinese Academy of Sciences · Pengcheng Laboratory · Memorax AI
CRAFT: Counterfactual Credit Assignment from Free Sibling Rollouts for Self-Distilled Agentic Reinforcement Learning
Jun 28, 2026Zibin Meng, Kani ChenAgentic RL KL-Regularized RL
The Hong Kong University of Science and Technology
Mesh-RL: Coupled subgrid reinforcement learning
Jun 24, 2026Behnam Gheshlaghi, Bahador Rashidi, Shahin AtakishiyevReinforcement Learning Credit Assignment in RL
Independent Researcher · University of Alberta
Semantic Consistency Policy Optimization for Reinforcement Learning of LLM Agents
Jun 24, 2026Peng Xu, Sijia Chen, Junzhuo Li +1Reward Shaping Credit Assignment in RL
†The Hong Kong University of Science and Technology (Guangzhou) · ‡The Hong Kong University of Science and Technology
Learning with a Single Rollout via Monte Carlo Pass@k Critic
Jun 24, 2026Fengdi Che, Yang Liu, Lei Yu +4RL for Language Model Reasoning Credit Assignment in RL
University of Alberta · BIGAI · University of Toronto +4
Learning Process Rewards via Success Visitation Matching for Efficient RL
Jun 22, 2026Raymond Tsao, Andrew Wagenmaker, Sergey LevineProcess Reward Models Credit Assignment in RL
UC Berkeley
Drowning in Routine: Signal Dilution in Multi-Turn Agent Training
Jun 20, 2026Yann Pernot, Vi RetaultReinforcement Learning Credit Assignment in RL
Mila - Québec AI Institute · Polytechnique Montréal

Aug 2, 2026, cs.CLJ/K move · Enter open · S save

EviSD: Evidence-Conditioned Self-Distillation for Search-Augmented Agents

Jianan Xie, Xin Sun, Zhongqi Chen, Xing Zheng+3

ShanghaiTech University · NLPR, MAIS, CASIA · Ant Group

Agentic Search Credit Assignment in RL Reinforcement Learning with Verifiable Rewards Self-Distillation RL for LLM Agents

Open paper AskPDF arXiv

Outcome-based reinforcement learning enables search-augmented language agents to learn from verifiable final answers, but its trajectory-level credit cannot distinguish the contributions of individual actions in a multi-turn search process. We propose EviSD, an evidence-conditioned self-distillation framework that uses instance-level supporting evidence as privileged information for search actions and golden answers as complementary privilege for answer actions. During training, the student samples actions from the original context, while the same model re-scores them as a privileged teacher under an action-aligned context. EviSD converts the detached teacher--student gap into a bounded correction to the outcome-derived GRPO advantage and applies it only to generated action spans. This design localizes privileged guidance while preserving the update direction determined by the outcome reward, without an auxiliary distillation objective or any change at inference time. Across seven question-answering benchmarks and three backbones spanning model scales and generations, EviSD achieves the highest macro-average Exact Match in all evaluated settings, outperforming the strongest compared methods by 1.3--2.3 points while modulating only 6.7%--15.1% of response tokens. Code is available at https://github.com/JiananXie/EviSD.

Momentum

Related topics

Latest papers 171