Imagen de Portada

Reward Modeling for Reinforcement Learning-Based LLM Reasoning: Design, Challenges, and Evaluation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Pan, Pei-Chi, Liang, Yingbin, Lin, Sen
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Algorithm Design for Online Meta-Learning with Task Boundary Detection
por: Sow, Daouda, et al.
Publicado: (2023)

Agentic Transformers Provably Learn to Search via Reinforcement Learning
por: Yang, Tong, et al.
Publicado: (2026)

Robust Offline Reinforcement Learning for Non-Markovian Decision Processes
por: Huang, Ruiquan, et al.
Publicado: (2024)

HIPO: Instruction Hierarchy via Constrained Reinforcement Learning
por: Chen, Keru, et al.
Publicado: (2026)

The Implicit Curriculum: Learning Dynamics in RL with Verifiable Rewards
por: Huang, Yu, et al.
Publicado: (2026)

Mixture-of-Transformers Learn Faster: A Theoretical Study on Classification Problems
por: Li, Hongbo, et al.
Publicado: (2025)

Reinforcing Multi-Turn Reasoning in LLM Agents via Turn-Level Reward Design
por: Wei, Quan, et al.
Publicado: (2025)

Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
por: Yang, Tong, et al.
Publicado: (2025)

Unlocking the Power of Rehearsal in Continual Learning: A Theoretical Perspective
por: Deng, Junze, et al.
Publicado: (2025)

Theory on Mixture-of-Experts in Continual Learning
por: Li, Hongbo, et al.
Publicado: (2024)

Regret Bounds for Reinforcement Learning from Multi-Source Imperfect Preferences
por: Shi, Ming, et al.
Publicado: (2026)

Near-Optimal Partially Observable Reinforcement Learning with Partial Online State Information
por: Shi, Ming, et al.
Publicado: (2023)

Binary Rewards and Reinforcement Learning: Fundamental Challenges
por: Dymetman, Marc
Publicado: (2026)

Reward Design for Reinforcement Learning Agents
por: Devidze, Rati
Publicado: (2025)

A Theoretical Analysis of Self-Supervised Learning for Vision Transformers
por: Huang, Yu, et al.
Publicado: (2024)

Focal Reward: Balanced Reinforcement Learning under Rubric-Based Rewards
por: Huang, Yu, et al.
Publicado: (2026)

RDA: Reward Design Agent for Reinforcement Learning
por: Lee, Hojoon, et al.
Publicado: (2026)

From Scores to Gibbs Correctors: Accelerating Uniform-Rate Discrete Diffusion Models
por: Liang, Yuchen, et al.
Publicado: (2026)

Self-Rewarding Rubric-Based Reinforcement Learning for Open-Ended Reasoning
por: Ye, Zhiling, et al.
Publicado: (2025)

Provable In-Context Learning of Nonlinear Regression with Transformers
por: Li, Hongbo, et al.
Publicado: (2025)

Decomposable Reward Modeling and Realistic Environment Design for Reinforcement Learning-Based Forex Trading
por: Saidd, Nabeel Ahmad
Publicado: (2026)

Provably Efficient UCB-type Algorithms For Learning Predictive State Representations
por: Huang, Ruiquan, et al.
Publicado: (2023)

Provably Sample-Efficient Robust Reinforcement Learning with Average Reward
por: Roch, Zachary, et al.
Publicado: (2025)

Step-wise Rubric Rewards for LLM Reasoning
por: Xie, Weichu, et al.
Publicado: (2026)

Alternating Reinforcement Learning for Rubric-Based Reward Modeling in Non-Verifiable LLM Post-Training
por: Xu, Ran, et al.
Publicado: (2026)

In-Context Learning with Representations: Contextual Generalization of Trained Transformers
por: Yang, Tong, et al.
Publicado: (2024)

Constraint-Rectified Training for Efficient Chain-of-Thought
por: Wu, Qinhang, et al.
Publicado: (2026)

Sharp Convergence Rates for Masked Diffusion Models
por: Liang, Yuchen, et al.
Publicado: (2026)

R^3: Replay, Reflection, and Ranking Rewards for LLM Reinforcement Learning
por: Jiang, Zhizheng, et al.
Publicado: (2026)

LinguaFluid: Language Guided Fluid Control via Semantic Rewards in Reinforcement Learning
por: Liang, Aoming, et al.
Publicado: (2025)

Linking Process to Outcome: Conditional Reward Modeling for LLM Reasoning
por: Zhang, Zheng, et al.
Publicado: (2025)

Rollout-Training Co-Design for Efficient LLM-Based Multi-Agent Reinforcement Learning
por: Jiang, Zhida, et al.
Publicado: (2026)

Binary Reward Labeling: Bridging Offline Preference and Reward-Based Reinforcement Learning
por: Xu, Yinglun, et al.
Publicado: (2024)

Theory on Score-Mismatched Diffusion Models and Zero-Shot Conditional Samplers
por: Liang, Yuchen, et al.
Publicado: (2024)

Information-Theoretic Reward Modeling for Stable RLHF: Detecting and Mitigating Reward Hacking
por: Miao, Yuchun, et al.
Publicado: (2025)

Parent-Guided Semantic Reward Model (PGSRM): Embedding-Based Reward Functions for Reinforcement Learning of Transformer Language Models
por: Plashchinsky, Alexandr
Publicado: (2025)

Risk-Averse Total-Reward Reinforcement Learning
por: Su, Xihong, et al.
Publicado: (2025)

Random Policy Valuation is Enough for LLM Reasoning with Verifiable Rewards
por: He, Haoran, et al.
Publicado: (2025)

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

ROAD: Responsibility-Oriented Reward Design for Reinforcement Learning in Autonomous Driving
por: Chen, Yongming, et al.
Publicado: (2025)