Image de couverture de livre

GPO: Learning from Critical Steps to Improve LLM Reasoning

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Yu, Jiahao, Cheng, Zelei, Wu, Xian, Xing, Xinyu
Format:	Preprint
Publié:	2025
Sujets:	Artificial Intelligence
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Building Coding Agents via Entropy-Enhanced Multi-Turn Preference Optimization
par: Yu, Jiahao, et autres
Publié: (2025)

A Survey on Explainable Deep Reinforcement Learning
par: Cheng, Zelei, et autres
Publié: (2025)

RICE: Breaking Through the Training Bottlenecks of Reinforcement Learning with Explanation
par: Cheng, Zelei, et autres
Publié: (2024)

Soft-Label Integration for Robust Toxicity Classification
par: Cheng, Zelei, et autres
Publié: (2024)

BlockScan: Detecting Anomalies in Blockchain Transactions
par: Yu, Jiahao, et autres
Publié: (2024)

CPL: Critical Plan Step Learning Boosts LLM Generalization in Reasoning Tasks
par: Wang, Tianlong, et autres
Publié: (2024)

Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning
par: Wu, Wenjie, et autres
Publié: (2025)

UC-MOA: Utility-Conditioned Multi-Objective Alignment for Distributional Pareto-Optimality
par: Cheng, Zelei, et autres
Publié: (2025)

GPTFUZZER: Red Teaming Large Language Models with Auto-Generated Jailbreak Prompts
par: Yu, Jiahao, et autres
Publié: (2023)

Pre-Act: Multi-Step Planning and Reasoning Improves Acting in LLM Agents
par: Rawat, Mrinal, et autres
Publié: (2025)

Offline Reinforcement Learning for LLM Multi-Step Reasoning
par: Wang, Huaijie, et autres
Publié: (2024)

PhGPO: Pheromone-Guided Policy Optimization for Long-Horizon Tool Planning
par: Li, Yu, et autres
Publié: (2026)

Step Guided Reasoning: Improving Mathematical Reasoning using Guidance Generation and Step Reasoning
par: Cao, Lang, et autres
Publié: (2024)

A Neuro-Symbolic Framework for Reasoning under Perceptual Uncertainty: Bridging Continuous Perception and Discrete Symbolic Planning
par: Wu, Jiahao, et autres
Publié: (2025)

rePIRL: Learn PRM with Inverse RL for LLM Reasoning
par: Wu, Xian, et autres
Publié: (2026)

Critical Tokens Matter: Token-Level Contrastive Estimation Enhances LLM's Reasoning Capability
par: Lin, Zicheng, et autres
Publié: (2024)

Adaptive Selection of Symbolic Languages for Improving LLM Logical Reasoning
par: Wang, Xiangyu, et autres
Publié: (2025)

Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
par: Zhen, Shuai, et autres
Publié: (2026)

LLM Reasoners: New Evaluation, Library, and Analysis of Step-by-Step Reasoning with Large Language Models
par: Hao, Shibo, et autres
Publié: (2024)

Asking the Right Questions: Improving Reasoning with Generated Stepping Stones
par: Hu, Hengyuan, et autres
Publié: (2026)

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
par: Wang, Yiding, et autres
Publié: (2025)

Scientific Logicality Enriched Methodology for LLM Reasoning: A Practice in Physics
par: Yu, Zhaoxin, et autres
Publié: (2026)

R3-RAG: Learning Step-by-Step Reasoning and Retrieval for LLMs via Reinforcement Learning
par: Li, Yuan, et autres
Publié: (2025)

SSPO: Self-traced Step-wise Preference Optimization for Process Supervision and Reasoning Compression
par: Xu, Yuyang, et autres
Publié: (2025)

Assessing Prompt Injection Risks in 200+ Custom GPTs
par: Yu, Jiahao, et autres
Publié: (2023)

Interactive Learning for LLM Reasoning
par: Lin, Hehai, et autres
Publié: (2025)

Reinforcement Learning Improves LLM Accuracy and Reasoning in Disease Classification from Radiology Reports
par: Wei, Yishu, et autres
Publié: (2026)

LLM Reasoning with Process Rewards for Outcome-Guided Steps
par: Rezaei, Mohammad, et autres
Publié: (2026)

On the Step Length Confounding in LLM Reasoning Data Selection
par: Wang, Bing, et autres
Publié: (2026)

Learning to Plan & Reason for Evaluation with Thinking-LLM-as-a-Judge
par: Saha, Swarnadeep, et autres
Publié: (2025)

Masked Thought: Simply Masking Partial Reasoning Steps Can Improve Mathematical Reasoning Learning of Language Models
par: Chen, Changyu, et autres
Publié: (2024)

On Information Self-Locking in Reinforcement Learning for Active Reasoning of LLM agents
par: Zou, Deyu, et autres
Publié: (2026)

Two-Stage Reasoning-Infused Learning: Improving Classification with LLM-Generated Reasoning
par: Henrichsen, Mads, et autres
Publié: (2025)

ProCeedRL: Process Critic with Exploratory Demonstration Reinforcement Learning for LLM Agentic Reasoning
par: Gao, Jingyue, et autres
Publié: (2026)

Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement
par: Xiong, Weimin, et autres
Publié: (2024)

Benchmarking Multi-Step Legal Reasoning and Analyzing Chain-of-Thought Effects in Large Language Models
par: Yu, Wenhan, et autres
Publié: (2025)

Discovering Process-Outcome Credit in Multi-Step LLM Reasoning
par: Wang, Xiangwei, et autres
Publié: (2026)

Beyond Meta-Reasoning: Metacognitive Consolidation for Self-Improving LLM Reasoning
par: Zhuang, Ziqing, et autres
Publié: (2026)

Experiential Reflective Learning for Self-Improving LLM Agents
par: Allard, Marc-Antoine, et autres
Publié: (2026)

ChestX-Reasoner: Advancing Radiology Foundation Models with Reasoning through Step-by-Step Verification
par: Fan, Ziqing, et autres
Publié: (2025)