Overview

Reward modeling turns comparisons, ratings, demonstrations, rubrics, or verifiable outcomes into signals for judging responses and actions. Methods range from pairwise preference models and scalar outcome or process critics to generative rubric judges, tool-based verifiers, and uncertainty-aware or personalized models. These signals guide preference optimization, best-of-N selection, test-time search, and training in language, image and video generation, robotics, and agents. A central challenge is that high preference accuracy may not capture diverse or shifting human intent, while optimization can exploit scoring biases, so evaluation must consider calibration and downstream behavior as well as ranking accuracy.

Latest papers

CardsList

340 papers21 papers in the last four weeks, down 56% on the four weeks before. 0.2% of all new papers.

  1. Adaptive Margin RLHF via Preference over Preferences

    Sep 26, 2025Yaswanth Chittepu, Prasann Singhal, Greg Durrett +1Pairwise Preference LearningReward Modeling

  2. Implicit Credit Learning for Sparse-Reward Multi-Agent Reinforcement Learning

    Sep 26, 2025The Viet Bui, Tien Mai, Hong Thanh NguyenCooperative MARLMulti-Agent Reinforcement Learning

  3. Aligning Audio Captions with Human Preferences

    Sep 18, 2025Kartik Hegde, Rehana Mahfuz, Yinyi Guo +1Reward ModelingAudio-Language Models

  4. MiCRo: Mixture Modeling and Context-aware Routing for Personalized Preference Learning

    May 30, 2025Jingyan Shen, Jiarui Yao, Rui Yang +5Pairwise Preference LearningReward Modeling

  5. R3: Robust Rubric-Agnostic Reward Models

    May 19, 2025David Anugraha, Zilu Tang, Lester James V. Miranda +5Reward ModelingLLM Evaluation

  6. Bias Fitting to Mitigate Length Bias of Reward Model in RLHF

    May 19, 2025Kangwen Zhao, Jianfeng Cai, Jinhua Zhu +5Reward ModelingLLM Alignment

  7. Two Minds Better Than One: Collaborative Reward Modeling for LLM Alignment

    May 15, 2025Jiazheng Zhang, Wenqing Jing, Zizhuo Zhang +12Reward ModelingLLM Alignment

  8. Supervised Reward Inference

    Feb 25, 2025Will Schwarzer, Jordan Schneider, Philip S. Thomas +1Reward ModelingReinforcement Learning

  9. AgentRM: Enhancing Agent Generalization with Reward Modeling

    Feb 25, 2025Yu Xia, Jingru Fan, Weize Chen +7Reward ModelingLLM Agents

  10. Dual Active Learning for Reinforcement Learning from Human Feedback

    Oct 3, 2024Pangpang Liu, Chengchun Shi, Will Wei SunRL from Human FeedbackPreference Learning for LLMs