Imagen de Portada

ReflectRM: Boosting Generative Reward Models via Self-Reflection within a Unified Judgment Framework

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Qin, Kai, Liu, Liangxin, Liang, Yu, Wang, Longzheng, Wang, Yan, Zhang, Yueyang, Xia, Long, Sun, Zhiyuan, Liu, Houde, Shi, Daiting
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Computation and Language
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

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

Advancing General-Purpose Reasoning Models with Modular Gradient Surgery
por: Cai, Min, et al.
Publicado: (2026)

When Less is More: The LLM Scaling Paradox in Context Compression
por: Guo, Ruishan, et al.
Publicado: (2026)

SelectIT: Selective Instruction Tuning for LLMs via Uncertainty-Aware Self-Reflection
por: Liu, Liangxin, et al.
Publicado: (2024)

TRE: Encouraging Exploration in the Trust Region
por: Huang, Chao, et al.
Publicado: (2026)

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

ROSD: Reflective On-Policy Self-Distillation for Language Model Reasoning across Domains
por: Zhao, Ziqi, et al.
Publicado: (2026)

Intuition First or Reflection Before Judgment? The Impact of Evaluation Sequence on Consumer Ratings
por: Wang, He, et al.
Publicado: (2025)

Thinking as Compression: Your Reasoning Model is Secretly a Context Compressor
por: Ma, Guoxin, et al.
Publicado: (2026)

MARS: Memory-Enhanced Agents with Reflective Self-improvement
por: Liang, Xuechen, et al.
Publicado: (2025)

Rewarding Reflection
por: Harvey, Carl A., II
Publicado: (2008)

HAF-RM: A Hybrid Alignment Framework for Reward Model Training
por: Liu, Shujun, et al.
Publicado: (2024)

Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
por: Hong, Ilgee, et al.
Publicado: (2025)

GUI-Reflection: Empowering Multimodal GUI Models with Self-Reflection Behavior
por: Wu, Penghao, et al.
Publicado: (2025)

Reflection in the Dark: Exposing and Escaping the Black Box in Reflective Prompt Optimization
por: Liu, Shiyan, et al.
Publicado: (2026)

Self-Verifying Reflection Helps Transformers with CoT Reasoning
por: Yu, Zhongwei, et al.
Publicado: (2025)

ReflectEvo: Improving Meta Introspection of Small LLMs by Learning Self-Reflection
por: Li, Jiaqi, et al.
Publicado: (2025)

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

CAMEL: Confidence-Gated Reflection for Reward Modeling
por: Zhu, Zirui, et al.
Publicado: (2026)

Phoenix: A Motion-based Self-Reflection Framework for Fine-grained Robotic Action Correction
por: Xia, Wenke, et al.
Publicado: (2025)

Enhancing Long-Chain Reasoning Distillation through Error-Aware Self-Reflection
por: Wu, Zhuoyang, et al.
Publicado: (2025)

GRPO and Reflection Reward for Mathematical Reasoning in Large Language Models
por: Wang, Zhijie
Publicado: (2026)

Self-Reflective Generation at Test Time
por: Mu, Jian, et al.
Publicado: (2025)

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

AlphaGRPO: Unlocking Self-Reflective Multimodal Generation in UMMs via Decompositional Verifiable Reward
por: Huang, Runhui, et al.
Publicado: (2026)

ALaRM: Align Language Models via Hierarchical Rewards Modeling
por: Lai, Yuhang, et al.
Publicado: (2024)

RL-RIG: A Generative Spatial Reasoner via Intrinsic Reflection
por: Wang, Tianyu, et al.
Publicado: (2026)

CE-RM: A Pointwise Generative Reward Model Optimized via Two-Stage Rollout and Unified Criteria
por: Hu, Xinyu, et al.
Publicado: (2026)

Judicial review and transitional justice: Reflective Judgment in three contexts
por: Mihaela Mihai
Publicado: (2010)

Think-Reflect-Revise: A Policy-Guided Reflective Framework for Safety Alignment in Large Vision Language Models
por: Weng, Fenghua, et al.
Publicado: (2025)

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

Reflecting Twice before Speaking with Empathy: Self-Reflective Alternating Inference for Empathy-Aware End-to-End Spoken Dialogue
por: Jia, Yuhang, et al.
Publicado: (2026)

Reflect, Retry, Reward: Self-Improving LLMs via Reinforcement Learning
por: Bensal, Shelly, et al.
Publicado: (2025)

CommSense: Facilitating Bias-Aware and Reflective Navigation of Online Comments for Rational Judgment
por: Ouyang, Yang, et al.
Publicado: (2026)

A Unified Representation Underlying the Judgment of Large Language Models
por: Lu, Yi-Long, et al.
Publicado: (2025)

Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning
por: Liu, Xinyu, et al.
Publicado: (2025)

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-Rewards
por: Hong, Jixiang, et al.
Publicado: (2025)

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

Reflection-Based Task Adaptation for Self-Improving VLA
por: Li, Baicheng, et al.
Publicado: (2025)

Meta-Reflection: A Feedback-Free Reflection Learning Framework
por: Wang, Yaoke, et al.
Publicado: (2024)