paper-with-me

홈 › Papers

Hindsight Credit Assignment for Long-Horizon LLM Agents

2026-03-07 · Hui-Ze Tan, Xiao-Wen Yang, Hao Chen, Jie-Jing Shao, Yi Wen, Yuteng Shen, Weihong Luo, Xiku Du, Lan-Zhe Guo, Yu-Feng Li arxiv

Large Language Model (LLM) agents often face significant credit assignment challenges in long-horizon, multi-step tasks due to sparse rewards. Existing value-free methods, such as Group Relative Policy Optimization (GRPO), encounter two fundamental bottlenecks: inaccurate step-level Q-value estimation and misaligned value baselines for intermediate states. To address these limitations, we introduce HCAPO, the first framework to integrate hindsight credit assignment into LLM agents. HCAPO leverages the LLM itself as a post-hoc critic to refine step-level Q-values through hindsight reasoning. Furthermore, HCAPO's multi-scale advantage mechanism effectively supplements the inaccurate value baselines at critical decision states. Evaluations across three challenging benchmarks, including WebShop and ALFWorld, demonstrate that HCAPO consistently outperforms state-of-the-art RL methods. Notably, HCAPO achieves a 7.7% improvement in success rate on WebShop and a 13.8% on ALFWorld over GRPO using the Qwen2.5-7B-Instruct model. These results indicate that HCAPO significantly enhances exploration efficiency, promotes concise decision-making, and ensures scalability in complex, long-horizon tasks.

📄 PDF Abstract BibTeX arXiv:2603.08754

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

HiMPO: Hindsight-Informed Memory Policy Optimization for Less-Entangled Credit in Long-Horizon Agents

2026-06-15 · Jiangze Yan, Yi Shen, Wenjing Zhang, Jieyun Huang 외 arxiv

Long-horizon agents rely on memory mechanisms to compress interaction history, but optimizing memory writing faces a distinct credit assignment challenge: a memory update may be rewarded or penalized due to downstream to…

Towards Causal Credit Assignment

2022-12-22 · Mátyás Schubert

Adequately assigning credit to actions for future outcomes based on their contributions is a long-standing open challenge in Reinforcement Learning. The assumptions of the most commonly used credit assignment method are …

counterfactual

Hindsight-DICE: Stable Credit Assignment for Deep Reinforcement Learning

2023-07-21 · Akash Velu, Skanda Vaidyanath, Dilip Arumugam

Oftentimes, environments for sequential decision-making problems can be quite sparse in the provision of evaluative feedback to guide reinforcement-learning agents. In the extreme case, long trajectories of behavior are …

Decision MakingDeep Reinforcement LearningOff-policy evaluationPolicy Gradient Methods+3

HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning

2026-03-19 · Zhicong Lu, Zichuan Lin, Wei Jia, Changyuan Tian 외 arxiv

While large language models excel in diverse domains, their performance on complex longhorizon agentic decision-making tasks remains limited. Most existing methods concentrate on designing effective reward models (RMs) t…

Reinforcement Learning

Milestone-Guided Policy Learning for Long-Horizon Language Agents

2026-05-07 · Zixuan Wang, Yuchen Yan, Hongxing Li, Teng Pan 외 arxiv

While long-horizon agentic tasks require language agents to perform dozens of sequential decisions, training such agents with reinforcement learning remains challenging. We identify two root causes: credit misattribution…

Reinforcement Learning