Image de couverture de livre

Agentic Reinforcement Learning with Implicit Step Rewards

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Liu, Xiaoqian, Wang, Ke, Wu, Yuchuan, Huang, Fei, Li, Yongbin, Zhang, Junge, Jiao, Jianbin
Format:	Preprint
Publié:	2025
Sujets:	Computation and Language
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

EPO: Explicit Policy Optimization for Strategic Reasoning in LLMs via Reinforcement Learning
par: Liu, Xiaoqian, et autres
Publié: (2025)

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization
par: Ye, Xinge, et autres
Publié: (2025)

MOA: Multi-Objective Alignment for Role-Playing Agents
par: Liao, Chonghua, et autres
Publié: (2025)

SDPO: Segment-Level Direct Preference Optimization for Social Agents
par: Kong, Aobo, et autres
Publié: (2025)

Fine-Tuning Language Models with Reward Learning on Policy
par: Lang, Hao, et autres
Publié: (2024)

Reward Modeling from Natural Language Human Feedback
par: Wang, Zongqi, et autres
Publié: (2026)

P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
par: Zhang, Pinyi, et autres
Publié: (2026)

FlowBench: Revisiting and Benchmarking Workflow-Guided Planning for LLM-based Agents
par: Xiao, Ruixuan, et autres
Publié: (2024)

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
par: Wang, Daoyu, et autres
Publié: (2026)

Stop Rewarding Hallucinated Steps: Faithfulness-Aware Step-Level Reinforcement Learning for Small Reasoning Models
par: Nie, Shuo, et autres
Publié: (2026)

TimeHC-RL: Temporal-aware Hierarchical Cognitive Reinforcement Learning for Enhancing LLMs' Social Intelligence
par: Hou, Guiyang, et autres
Publié: (2025)

Self-supervised Pretraining for Decision Foundation Model: Formulation, Pipeline and Challenges
par: Liu, Xiaoqian, et autres
Publié: (2023)

Enhancing the General Agent Capabilities of Low-Parameter LLMs through Tuning and Multi-Branch Reasoning
par: Zhou, Qinhao, et autres
Publié: (2024)

OpenReward: Learning to Reward Long-form Agentic Tasks via Reinforcement Learning
par: Hu, Ziyou, et autres
Publié: (2025)

RLAR: An Agentic Reward System for Multi-task Reinforcement Learning on Large Language Models
par: Feng, Andrew Zhuoer, et autres
Publié: (2026)

Reinforcement Learning with Verifiable Rewards Implicitly Incentivizes Correct Reasoning in Base LLMs
par: Wen, Xumeng, et autres
Publié: (2025)

Reverse Preference Optimization for Complex Instruction Following
par: Huang, Xiang, et autres
Publié: (2025)

Process Reinforcement through Implicit Rewards
par: Cui, Ganqu, et autres
Publié: (2025)

CogDual: Enhancing Dual Cognition of LLMs via Reinforcement Learning with Implicit Rule-Based Rewards
par: Liu, Cheng, 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)

Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity
par: Fang, Feiteng, et autres
Publié: (2025)

Socratic-PRMBench: Benchmarking Process Reward Models with Systematic Reasoning Patterns
par: Li, Xiang, et autres
Publié: (2025)

Code Aesthetics with Agentic Reward Feedback
par: Xiao, Bang, et autres
Publié: (2025)

Curing Miracle Steps in LLM Mathematical Reasoning with Rubric Rewards
par: Yuan, Youliang, et autres
Publié: (2025)

Self-Guided Process Reward Optimization with Redefined Step-wise Advantage for Process Reinforcement Learning
par: Fei, Wu, et autres
Publié: (2025)

LogicReward: Incentivizing LLM Reasoning via Step-Wise Logical Supervision
par: Xu, Jundong, et autres
Publié: (2025)

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
par: Gao, Shiping, et autres
Publié: (2026)

Safe Reinforcement Learning with Free-form Natural Language Constraints and Pre-Trained Language Models
par: Lou, Xingzhou, et autres
Publié: (2024)

StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning
par: Yu, Yuanqing, et autres
Publié: (2024)

Improving Factual Consistency of News Summarization by Contrastive Preference Optimization
par: Feng, Huawen, et autres
Publié: (2023)

Position: Foundation Agents as the Paradigm Shift for Decision Making
par: Liu, Xiaoqian, et autres
Publié: (2024)

Full-Step-DPO: Self-Supervised Preference Optimization with Step-wise Rewards for Mathematical Reasoning
par: Xu, Huimin, et autres
Publié: (2025)

DeltaMem: Towards Agentic Memory Management via Reinforcement Learning
par: Zhang, Qi, et autres
Publié: (2026)

ToolRM: Towards Agentic Tool-Use Reward Modeling
par: Li, Renhao, et autres
Publié: (2025)

Debate Helps Weak-to-Strong Generalization
par: Lang, Hao, et autres
Publié: (2025)

Selective Weak-to-Strong Generalization
par: Lang, Hao, et autres
Publié: (2025)

Distribution-Aware Reward Estimation for Test-Time Reinforcement Learning
par: Du, Bodong, et autres
Publié: (2026)

Zero-Shot Detection of LLM-Generated Text via Implicit Reward Model
par: Liu, Runheng, et autres
Publié: (2026)

Fortify the Shortest Stave in Attention: Enhancing Context Awareness of Large Language Models for Effective Tool Use
par: Chen, Yuhan, et autres
Publié: (2023)

HISR: Hindsight Information Modulated Segmental Process Rewards For Multi-turn Agentic Reinforcement Learning
par: Lu, Zhicong, et autres
Publié: (2026)