Cover Image

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Hong, Ilgee, Yu, Changlong, Qiu, Liang, Yan, Weixiang, Xu, Zhenghao, Jiang, Haoming, Zhang, Qingru, Lu, Qin, Liu, Xin, Zhang, Chao, Zhao, Tuo
Format:	Preprint
Published:	2025
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Ask a Strong LLM Judge when Your Reward Model is Uncertain
by: Xu, Zhenghao, et al.
Published: (2025)

Discriminative Finetuning of Generative Large Language Models without Reward Models and Human Preference Data
by: Guo, Siqi, et al.
Published: (2025)

Self-Rewarding PPO: Aligning Large Language Models with Demonstrations Only
by: Zhang, Qingru, et al.
Published: (2025)

Robust Reinforcement Learning from Corrupted Human Feedback
by: Bukharin, Alexander, et al.
Published: (2024)

Approximation of Log-Partition Function in Policy Mirror Descent Induces Implicit Regularization for LLM Post-Training
by: Xu, Zhenghao, et al.
Published: (2026)

Fast-Slow Thinking RM: Efficient Integration of Scalar and Generative Reward Models
by: Wu, Jiayun, et al.
Published: (2026)

LongRM: Revealing and Unlocking the Context Boundary of Reward Modeling
by: Tang, Zecheng, et al.
Published: (2025)

Adaptive Preference Scaling for Reinforcement Learning with Human Feedback
by: Hong, Ilgee, et al.
Published: (2024)

OpenRubrics: Towards Scalable Synthetic Rubric Generation for Reward Modeling and LLM Alignment
by: Liu, Tianci, et al.
Published: (2025)

AgentRM: Enhancing Agent Generalization with Reward Modeling
by: Xia, Yu, et al.
Published: (2025)

RM-R1: Reward Modeling as Reasoning
by: Chen, Xiusi, et al.
Published: (2025)

SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
by: Fan, Kaixuan, et al.
Published: (2025)

InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
by: Yan, Yuchen, et al.
Published: (2026)

ConsistRM: Improving Generative Reward Models via Consistency-Aware Self-Training
by: Liang, Yu, et al.
Published: (2026)

SlimMoE: Structured Compression of Large MoE Models via Expert Slimming and Distillation
by: Li, Zichong, et al.
Published: (2025)

InfoRM: Mitigating Reward Hacking in RLHF via Information-Theoretic Reward Modeling
by: Miao, Yuchun, et al.
Published: (2024)

ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework
by: Qin, Kai, et al.
Published: (2026)

Mem-T: Densifying Rewards for Long-Horizon Memory Agents
by: Yue, Yanwei, et al.
Published: (2026)

Search More, Think Less: Rethinking Long-Horizon Agentic Search for Efficiency and Generalization
by: Chen, Qianben, et al.
Published: (2026)

Think Through Uncertainty: Improving Long-Form Generation Factuality via Reasoning Calibration
by: Liu, Xin, et al.
Published: (2026)

PRMB: Benchmarking Reward Models in Long-Horizon CBT-based Counseling Dialogue
by: Zhou, Yougen, et al.
Published: (2026)

Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
by: Zhang, Zhen, et al.
Published: (2025)

RLVMR: Reinforcement Learning with Verifiable Meta-Reasoning Rewards for Robust Long-Horizon Agents
by: Zhang, Zijing, et al.
Published: (2025)

AlphaQuanter: An End-to-End Tool-Augmented Agentic Reinforcement Learning Framework for Stock Trading
by: Deng, Zheye, et al.
Published: (2025)

ProgRM: Build Better GUI Agents with Progress Rewards
by: Zhang, Danyang, et al.
Published: (2025)

RM-Distiller: Exploiting Generative LLM for Reward Model Distillation
by: Zhou, Hongli, et al.
Published: (2026)

DyCoRM: Dynamic Criterion-Aware Reward Modeling for Text-to-Image Generation
by: Qian, Jiaying, et al.
Published: (2026)

WebAnchor: Anchoring Agent Planning to Stabilize Long-Horizon Web Reasoning
by: Yu, Xinmiao, et al.
Published: (2026)

Thinking in Text and Images: Interleaved Vision--Language Reasoning Traces for Long-Horizon Robot Manipulation
by: Liu, Jinkun, et al.
Published: (2026)

VR-Thinker: Boosting Video Reward Models through Thinking-with-Image Reasoning
by: Wang, Qunzhong, et al.
Published: (2025)

EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
by: Liu, Lulin, et al.
Published: (2026)

RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems
by: Zeng, Wenwen, et al.
Published: (2026)

Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation
by: Zhang, Yuwei, et al.
Published: (2026)

GEAR: An Efficient KV Cache Compression Recipe for Near-Lossless Generative Inference of LLM
by: Kang, Hao, et al.
Published: (2024)

Can RL Teach Long-Horizon Reasoning to LLMs? Expressiveness Is Key
by: Wang, Tianle, et al.
Published: (2026)

SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
by: Zhao, Bingchen, et al.
Published: (2026)

Keyframe-Guided Structured Rewards for Reinforcement Learning in Long-Horizon Laboratory Robotics
by: Qiu, Yibo, et al.
Published: (2026)

SteerRM: Debiasing Reward Models via Sparse Autoencoders
by: Sun, Mengyuan, et al.
Published: (2026)

Learning to Optimize Multi-Objective Alignment Through Dynamic Reward Weighting
by: Lu, Yining, et al.
Published: (2025)

P-GenRM: Personalized Generative Reward Model with Test-time User-based Scaling
by: Zhang, Pinyi, et al.
Published: (2026)