Imagen de Portada

Boosting Universal LLM Reward Design through Heuristic Reward Observation Space Evolution

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Heng, Zen Kit, Zhao, Zimeng, Wu, Tianhao, Wang, Yuanfei, Wu, Mingdong, Wang, Yangang, Dong, Hao
Formato:	Preprint
Publicado:	2025
Materias:	Artificial Intelligence
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

GraspGF: Learning Score-based Grasping Primitive for Human-assisting Dexterous Grasping
por: Wu, Tianhao, et al.
Publicado: (2023)

DiffusionReward: Enhancing Blind Face Restoration through Reward Feedback Learning
por: Wu, Bin, et al.
Publicado: (2025)

AdaManip: Adaptive Articulated Object Manipulation Environments and Policy Learning
por: Wang, Yuanfei, et al.
Publicado: (2025)

Reward Shaping to Mitigate Reward Hacking in RLHF
por: Fu, Jiayi, et al.
Publicado: (2025)

Towards Socially and Morally Aware RL agent: Reward Design With LLM
por: Wang, Zhaoyue
Publicado: (2024)

Automatic Reward Shaping from Multi-Objective Human Heuristics
por: Xie, Yuqing, et al.
Publicado: (2025)

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

Meta-Rewarding Language Models: Self-Improving Alignment with LLM-as-a-Meta-Judge
por: Wu, Tianhao, et al.
Publicado: (2024)

Boosting LLM Reasoning via Human-Inspired Reward Shaping
por: Lin, Wenze, et al.
Publicado: (2026)

Incentivizing Parametric Knowledge via Reinforcement Learning with Verifiable Rewards for Cross-Cultural Entity Translation
por: Zhou, Jiang, et al.
Publicado: (2026)

Enhancing CVRP Solver through LLM-driven Automatic Heuristic Design
por: Xie, Zhuoliang, et al.
Publicado: (2026)

Co-Evolution of Policy and Internal Reward for Language Agents
por: Wang, Xinyu, et al.
Publicado: (2026)

Reward Model Routing in Alignment
por: Wu, Xinle, et al.
Publicado: (2025)

Large Reward Models: Generalizable Online Robot Reward Generation with Vision-Language Models
por: Wu, Yanru, et al.
Publicado: (2026)

MAESTRO: Multi-Agent Environment Shaping through Task and Reward Optimization
por: Wu, Boyuan
Publicado: (2025)

Beyond Reward Hacking: Causal Rewards for Large Language Model Alignment
por: Wang, Chaoqi, et al.
Publicado: (2025)

Training LLM Agents for Spontaneous, Reward-Free Self-Evolution via World Knowledge Exploration
por: Zhang, Qifan, et al.
Publicado: (2026)

IPD: Boosting Sequential Policy with Imaginary Planning Distillation in Offline Reinforcement Learning
por: Qin, Yihao, et al.
Publicado: (2026)

Enhancing LLM Reasoning with Reward-guided Tree Search
por: Jiang, Jinhao, et al.
Publicado: (2024)

Structural Reward Model: Enhancing Interpretability, Efficiency, and Scalability in Reward Modeling
por: Liu, Xiaoyu, et al.
Publicado: (2025)

SemiReward: A General Reward Model for Semi-supervised Learning
por: Li, Siyuan, et al.
Publicado: (2023)

BEAM: Bi-level Memory-adaptive Algorithmic Evolution for LLM-Powered Heuristic Design
por: Xiang, Chuyang, et al.
Publicado: (2026)

RHyVE: Competence-Aware Verification and Phase-Aware Deployment for LLM-Generated Reward Hypotheses
por: Wu, Feiyu, et al.
Publicado: (2026)

Optimal Transport for LLM Reward Modeling from Noisy Preference
por: Pan, Licheng, et al.
Publicado: (2026)

Verifiable Process Rewards for Agentic Reasoning
por: Yuan, Huining, et al.
Publicado: (2026)

WildReward: Learning Reward Models from In-the-Wild Human Interactions
por: Peng, Hao, et al.
Publicado: (2026)

From Reward Shaping to Q-Shaping: Achieving Unbiased Learning with LLM-Guided Knowledge
por: Wu, Xiefeng
Publicado: (2024)

Enhancing Inverse Reinforcement Learning through Encoding Dynamic Information in Reward Shaping
por: Zhan, Simon Sinong, et al.
Publicado: (2024)

RoboAlign-R1: Distilled Multimodal Reward Alignment for Robot Video World Models
por: Wu, Hao, et al.
Publicado: (2026)

G-LNS: Generative Large Neighborhood Search for LLM-Based Automatic Heuristic Design
por: Zhao, Baoyun, et al.
Publicado: (2026)

TIDE: Tuning-Integrated Dynamic Evolution for LLM-Based Automated Heuristic Design
por: Chen, Chentong, et al.
Publicado: (2026)

Process Reinforcement through Implicit Rewards
por: Cui, Ganqu, et al.
Publicado: (2025)

Automated Reward Design for Gran Turismo
por: Ma, Michel, et al.
Publicado: (2025)

Tiered Reward: Designing Rewards for Specification and Fast Learning of Desired Behavior
por: Zhou, Zhiyuan, et al.
Publicado: (2022)

What Are Step-Level Reward Models Rewarding? Counterintuitive Findings from MCTS-Boosted Mathematical Reasoning
por: Ma, Yiran, et al.
Publicado: (2024)

Auto MC-Reward: Automated Dense Reward Design with Large Language Models for Minecraft
por: Li, Hao, et al.
Publicado: (2023)

Extracting Heuristics from Large Language Models for Reward Shaping in Reinforcement Learning
por: Bhambri, Siddhant, et al.
Publicado: (2024)

Beyond Outcome Reward: Decoupling Search and Answering Improves LLM Agents
por: Wang, Yiding, et al.
Publicado: (2025)

Metacognition as Reward: Reinforcing LLM Reasoning via Knowledge and Regulation Signals
por: Chen, Sirui, et al.
Publicado: (2026)

MT-RewardTree: A Comprehensive Framework for Advancing LLM-Based Machine Translation via Reward Modeling
por: Feng, Zhaopeng, et al.
Publicado: (2025)