paper-with-me

홈 › Papers

CriticSearch: Fine-Grained Credit Assignment for Search Agents via a Retrospective Critic

2025-11-15 · Yaocheng Zhang, Haohuan Huang, Zijun Song, Yuanheng Zhu, Qichao Zhang, Zijie Zhao, Dongbin Zhao arxiv

Tool-Integrated Reasoning (TIR) with search engines enables large language models to iteratively retrieve up-to-date external knowledge, enhancing adaptability and generalization in complex question-answering tasks. However, existing search agent pipelines typically depend on reinforcement learning based optimization, which often suffers from sparse outcome rewards, leading to inefficient exploration and unstable training. We introduce CriticSearch, a fine-grained credit-assignment framework that supplies dense, turn-level feedback via a retrospective critic mechanism. During training, a frozen, asymmetric critique LLM retrospectively evaluates each turn using privileged information from the full trajectory and gold answers, converting these assessments into stable, dense rewards that guide policy improvement. Experimental results across diverse multi-hop reasoning benchmarks demonstrate that CriticSearch consistently outperforms existing baselines, achieving faster convergence, improved training stability, and higher performance.

📄 PDF Abstract BibTeX arXiv:2511.12159

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

GeneralThinker: Domain-General Reasoning through Likelihood-Guided Answer-Conditioned Optimization

2026-05-27 · Shengmin Piao, Sanghyun Park arxiv

Reinforcement learning with verifiable rewards improves language model reasoning, but its reliance on domain-specific verifiers, sparse outcome rewards, and coarse-grained credit assignment limits its applicability. We i…

Reinforcement Learning

TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents

2026-08-17 · Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv 외 arxiv

Long-horizon large language model (LLM) agents are typically optimized with sparse terminal outcomes, making fine-grained credit assignment across multi-step interactions difficult. Existing approaches either rely on pro…

Reinforcement Learning

PBSD: Privileged Bayesian Self-Distillation for Long-Horizon Credit Assignment

2026-06-08 · Yang Tian, Rui Wang, Xumeng Wen, Junjie Li 외 arxiv

Long-horizon agentic tasks pose a fundamental credit assignment challenge for outcome-base reinforcement learning: trajectory-level rewards verify final correctness but provide limited guidance on which intermediate reas…

Reinforcement Learning

SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More

2026-01-09 · Muye Huang, Lingling Zhang, Yifei Li, Yaqiang Wu 외 arxiv

Charts are high-density visual carriers of complex data and medium for information extraction and analysis. Due to the need for precise and complex visual reasoning, automated chart understanding poses a significant chal…

Reinforcement LearningInformation ExtractionVisual Reasoning

From Credit Assignment to Entropy Regularization: Two New Algorithms for Neural Sequence Prediction

2018-04-29 · ACL 2018 7 · Zihang Dai, Qizhe Xie, Eduard Hovy

In this work, we study the credit assignment problem in reward augmented maximum likelihood (RAML) learning, and establish a theoretical equivalence between the token-level counterpart of RAML and the entropy regularized…

Predictionreinforcement-learningReinforcement LearningReinforcement Learning (RL)