Imagen de Portada

Enhancing Agentic RL with Progressive Reward Shaping and Value-based Sampling Policy Optimization

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Su, Jianghao, Zeng, Xia, Liu, Luhui, Luo, Chao, Chen, Ye, Zhuang, Zhuoran
Formato:	Preprint
Publicado:	2025
Materias:	Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards
por: Zeng, Xia, et al.
Publicado: (2025)

ACE-RL: Adaptive Constraint-Enhanced Reward for Long-form Generation Reinforcement Learning
por: Chen, Jianghao, et al.
Publicado: (2025)

AgentV-RL: Scaling Reward Modeling with Agentic Verifier
por: Zhang, Jiazheng, et al.
Publicado: (2026)

On-Policy RL with Optimal Reward Baseline
por: Hao, Yaru, et al.
Publicado: (2025)

Multi-Objective and Mixed-Reward Reinforcement Learning via Reward-Decorrelated Policy Optimization
por: Bai, Yang, et al.
Publicado: (2026)

SAIL-RL: Guiding MLLMs in When and How to Think via Dual-Reward RL Tuning
por: Shu, Fangxun, et al.
Publicado: (2025)

Crossing the Reward Bridge: Expanding RL with Verifiable Rewards Across Diverse Domains
por: Su, Yi, et al.
Publicado: (2025)

Math-PUMA: Progressive Upward Multimodal Alignment to Enhance Mathematical Reasoning
por: Zhuang, Wenwen, et al.
Publicado: (2024)

Discriminative Policy Optimization for Token-Level Reward Models
por: Chen, Hongzhan, et al.
Publicado: (2025)

EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget
por: Chen, Liang, et al.
Publicado: (2025)

The Past Is Not Past: Memory-Enhanced Dynamic Reward Shaping
por: Liu, Yang, et al.
Publicado: (2026)

LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks
por: Wan, Jiayong, et al.
Publicado: (2026)

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models
por: Feng, Xiao, et al.
Publicado: (2026)

Search-P1: Path-Centric Reward Shaping for Stable and Efficient Agentic RAG Training
por: Xia, Tianle, et al.
Publicado: (2026)

When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards
por: Fan, Mingyuan, et al.
Publicado: (2026)

RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
por: Li, Gaotang, et al.
Publicado: (2026)

StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
por: Wang, Daoyu, et al.
Publicado: (2026)

A$^2$TGPO: Agentic Turn-Group Policy Optimization with Adaptive Turn-level Clipping
por: Chen, Dingwei, et al.
Publicado: (2026)

Agentic Reinforced Policy Optimization
por: Dong, Guanting, et al.
Publicado: (2025)

Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
por: Gao, Shiping, et al.
Publicado: (2026)

Offline RL by Reward-Weighted Fine-Tuning for Conversation Optimization
por: Mukherjee, Subhojyoti, et al.
Publicado: (2025)

AT$^2$PO: Agentic Turn-based Policy Optimization via Tree Search
por: Zong, Zefang, et al.
Publicado: (2026)

GTPO and GRPO-S: Token and Sequence-Level Reward Shaping with Policy Entropy
por: Tan, Hongze, et al.
Publicado: (2025)

CPO: Addressing Reward Ambiguity in Role-playing Dialogue via Comparative Policy Optimization
por: Ye, Xinge, et al.
Publicado: (2025)

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Markov Likelihood
por: Lin, Xingyu, et al.
Publicado: (2025)

Agentic Reinforcement Learning with Implicit Step Rewards
por: Liu, Xiaoqian, et al.
Publicado: (2025)

Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
por: Kang, Minki, et al.
Publicado: (2026)

Sotopia-RL: Reward Design for Social Intelligence
por: Yu, Haofei, et al.
Publicado: (2025)

SPEC-RL: Accelerating On-Policy Reinforcement Learning with Speculative Rollouts
por: Liu, Bingshuai, et al.
Publicado: (2025)

Code Aesthetics with Agentic Reward Feedback
por: Xiao, Bang, et al.
Publicado: (2025)

Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
por: Guo, Yiran, et al.
Publicado: (2025)

Understanding How Value Neurons Shape the Generation of Specified Values in LLMs
por: Su, Yi, et al.
Publicado: (2025)

Agent-RewardBench: Towards a Unified Benchmark for Reward Modeling across Perception, Planning, and Safety in Real-World Multimodal Agents
por: Men, Tianyi, et al.
Publicado: (2025)

Text2Reward: Reward Shaping with Language Models for Reinforcement Learning
por: Xie, Tianbao, et al.
Publicado: (2023)

ToolRM: Towards Agentic Tool-Use Reward Modeling
por: Li, Renhao, et al.
Publicado: (2025)

Token-Level Policy Optimization: Linking Group-Level Rewards to Token-Level Aggregation via Sequence-Level Likelihood
por: Lin, Xingyu, et al.
Publicado: (2026)

Building Autonomous GUI Navigation via Agentic-Q Estimation and Step-Wise Policy Optimization
por: Wang, Yibo, et al.
Publicado: (2026)

Enhancing Judgment Document Generation via Agentic Legal Information Collection and Rubric-Guided Optimization
por: Su, Weihang, et al.
Publicado: (2026)

On Designing Effective RL Reward at Training Time for LLM Reasoning
por: Gao, Jiaxuan, et al.
Publicado: (2024)

InfoFlow: Reinforcing Search Agent Via Reward Density Optimization
por: Luo, Kun, et al.
Publicado: (2025)