Critic

Ask about this topic

Momentum

17 papers in the last four weeks, up 240% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 58

All topics
CardsList

  1. After Cooperation Is Learned: Gradient Routing and Optimizer-Dependent Maintenance in Multi-Agent Reinforcement Learning

    Oct 1, 2026Chaoyuan Hao, Wentao Yue, Tianyou Lai +4Multi-Agent Reinforcement LearningCooperation

  2. Role-Adaptive Policy Optimization for Offline Reinforcement Learning

    Sep 30, 2026Seonvin Cho, Soohyun Choi, Songnam HongFrictive Policy OptimizationOffline Reinforcement Learning

    Department of Electronic Engineering, Hanyang University Seoul, Republic of Korea

  3. Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction

    Sep 30, 2026Xiao Cui, Mo Zhu, Yulei Qin +3Dataset DistillationOn-Policy

    University of Science and Technology of China · Zhejiang University · Independent Researcher

  4. Beyond Policy Alignment: Closing the Planning-Learning Loop for Robot Control with Learned World Models

    Sep 30, 2026Kowndinya Boyalakuntla, Yuhan Liu, Abdeslam BoulariasWorld Model PlanningModel Predictive Control

    Rutgers University

  5. Trust the Critic More

    Sep 30, 2026Kaiyue Wen, Luke Bailey, Arvind Mahankali +1Critic-Free Reinforcement LearningLarge Language Model Reinforcement Learning

    Stanford University

  6. Privy to the Foil: Recasting Value Estimation with a Self-Privileged Critic for RLVR

    Sep 29, 2026Kun Liang, Chenming Tang, Clive Bai +5Reinforcement Learning With Verifiable RewardSoft Actor-Critic

    School of Computer Science, Peking University · National Key Laboratory for Multimedia Information Processing, Peking University · Foundation Model Department, Tencent

  7. ReF-HIL: Shaping the Critic around Human Action Neighborhoods for Efficient Human-in-the-Loop Reinforcement Learning

    Sep 29, 2026Shaoyin Luo, Song Wang, Shibo Xia +5Reinforcement Learning From Human FeedbackHuman-In-The-Loop

    Department of Mechanical Engineering, Tsinghua University, Beijing 100084, China

  8. Unlocking the Critic: Reward-Free Policy Optimization for LLM Post-Training

    Sep 29, 2026Hongyang Li, Xiao Li, Caesar Wu +3Critic-Free Reinforcement LearningReward-Only Policy Optimization Variants

    University of Luxembourg · Seafill Open-Source Community · Université Paris-Saclay

  9. Diffusion Policy Improvement with Proposal-Conditioned Refinement Flows

    Sep 29, 2026Junhyun Ha, Juho Lee, Byoungwoo ParkFlow PoliciesDiffusion-Based Reinforcement Learning Methods

    KAIST

  10. PDMD: Projected Distribution Matching Distillation for Video Diffusion Models

    Sep 28, 2026Zimo Wang, Junkun Yuan, Angtian Wang +9Video Diffusion ModelsDistribution Matching Distillation

    University of California, San Diego · ByteDance Inc.

  11. Adjoint Guidance Flow: Amortized Critic Guidance for VLA Policies

    Sep 28, 2026Jeongsol Kim, Youngjun Jun, Kyumin Choi +6Flow-Matching Vision-Language-ActionCritic-Free Reinforcement Learning

    KAIST · SKKU · GIST

  12. SpeechCritic: Learning a Diagnostic Speech Judge from Limited Human Preferences

    Sep 28, 2026Mingyue Huo, Shivam Mehta, Bhavin Jawade +2Large Audio Language ModelsCritic

    University of Illinois Urbana-Champaign · Netflix

  13. Opera: A Verbal Critic Framework for Long-horizon Coding Agents

    Sep 27, 2026Kai Mei, Zhiyuan Hu, Yutong Dai +7CriticLong-Horizon Agents

    Salesforce AI Research · Rutgers University · Lehigh University

  14. On Preference Coverage Collapse from Hindsight Relabeling in Multi-Objective Reinforcement Learning

    Sep 22, 2026Baptiste Bonin, Caro Strickland, Audrey DurandMulti-Objective Reinforcement LearningHindsight

    Mila (Quebec AI Institute) · Université Laval · CIFAR AI Chair

  15. PACT: From Credit Assignment to Critic Alignment

    Sep 22, 2026Jiayan Fu, Hang Xu, Yong Zhang +4Critic-Free Reinforcement LearningCredit Assignment

    AllSpark Team

  16. ExecCritic: Learn to Test, Test to Improve for Coding Agents

    Sep 8, 2026Leitian Tao, Baolin Peng, Haorui Wang +7Coding AgentsTest Generation

    University of Wisconsin–Madison · Microsoft Research · Georgia Tech

  17. Better Call CineCrew: Consistent Ultra-Long Narrative-to-Film Generation

    Sep 7, 2026Jiaben Chen, Sixun Dong, Qinhong Zhou +4Cinematic IdealFilms

    University of Massachusetts Amherst, Amherst, MA 01003, USA · Massachusetts Institute of Technology, Cambridge, MA 02139, USA

  18. LOCI: A Locator-Critic with Refinement Loop

    Aug 31, 2026Walid Bousselham, Mathilde Caron, Arsha Nagrani +1Recent Vision-Language ModelsVisual Evidence

    Google DeepMind

  19. Locally-Guided Actor-Critic: Training a Goal-conditioned Actor with a Subgoal-aware Critic

    Aug 31, 2026Olivier Serris, Stéphane Doncieux, Olivier SigaudGoal-Conditioned Reinforcement LearningPotential-Based Reward Shaping

    ISIR · Sorbonne Université, CNRS

  20. Co-Evolving Actor-Conditioned Critics for Non-Verifiable Generation

    Aug 31, 2026Jinyoung Kim, Muhammad Khalifa, Lajanugen Logeswaran +4CritiqueCritic

    University of Michigan · LG AI Research · University of Illinois at Chicago

  21. Recovering Expert Critic-Sourced Network Adjacency between Musical Artists from Acoustic Distributions: A Construct-Validity Approach

    Aug 27, 2026Elena Badillo-Goicoechea, Fengfeng HeCollaborative FilteringSymbolic Music Generation

    University of Chicago Chicago, Illinois, USA

  22. Critic-Free Pretraining for Efficient Online Reinforcement Learning Fine-Tuning

    Aug 11, 2026Daoyi Li, Yixian Zhang, Wenbo Ding +2Soft Actor-CriticBoltzmann Policies

    Tsinghua University

  23. CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning

    Aug 7, 2026Ibne Farabi Shihab, Sanjeda Akter, Abu Sa-Adat Mohamed Moon-Im Al Ahsan +2Model-Based Reinforcement LearningOffline Reinforcement Learning

    Department of Computer Science, Iowa State University · Department of Computer Science & Engineering, BRAC University · Department of Civil, Construction & Environmental Engineering, Iowa State University

  24. Optimizing What Policies Learn From: Recoverability-aware Rollout Intervention Learning

    Aug 5, 2026Zheyuan Zhang, Manqing Mao, Hong Wang +8Group-Based Reinforcement LearningRollout

    University of Notre Dame · Amazon, Inc

  25. Start Classifying: Categorical Critics for LLM Reinforcement Learning

    Aug 3, 2026Zhijian Zhou, Long Li, Xuan Zhang +7Large Language Model Reinforcement LearningCritic-Free Reinforcement Learning

    Fudan University · Shanghai Innovation Institute · Tencent YoutuLab +2

  26. LEAP: Lean Environment-Feedback via Adaptive Pruning for Code RL in GPU Kernel Generation

    Aug 3, 2026Tankun Li, Zhi Chen, Yaohua TangGraphics Processing Unit KernelsCode Optimization

    Moore Threads AI

  27. WCM: A World Critic Model for Vision-Language-Action Reinforcement Learning

    Jul 31, 2026Senyu Fei, Xiaopeng Yu, Siyin Wang +3Diffusion-Based Vision-Language-ActionsEfficient World-Action Model

    1Tongji University · 3Fudan University · 2Shanghai Innovation Institute

  28. Offline-Online Curriculum RL for Multimodal Reasoning

    Jul 26, 2026Wendi Deng, Hang Du, Guoshun Nan +11Multimodal ReasoningCurriculum Reinforcement Learning

    Beijing University of Posts and Telecommunications, Beijing, 100876, China. · BUPT Shenzhen Institute, ShenZhen, 518038, China. · Carnegie Mellon University, Pittsburgh, USA. +4

  29. Adversarial Test-Hardening for AI-Written Code: An Instrument Autopsy and a Pre-Registered Causal Estimate of the Critic Loop

    Jul 25, 2026Jeff OttersonCode QualityAdversarial Evaluation

    W. P. Carey School of Business, Arizona State University

  30. TriAgent: Divergence-Aware Multi-Agent Committees for Cost-Efficient Financial Sentiment Analysis

    Jul 22, 2026Isabel Xu, Cynthia Xu, Rachel Ren +2Financial Sentiment AnalysisReasoning Skills

    The Overlake School · 1The Overlake School · Edwards Vacuum Inc. +3

  31. HCPG-Flow:Hierarchical Contact-Progress Guidance for Flow-Policy Robot Manipulation

    Jul 20, 2026Guanghu Xie, Mingxu Li, Shuo Zhang +5Multimodal Action DistributionsRobotic Manipulation

    State Key Laboratory of Robotics and Systems, Harbin Institute of Technology, Harbin 150001, Heilongjiang, China

  32. From Critic to Confidence: PPO for Language-Based Quantitative Prediction with Confidence Estimation

    Jul 14, 2026Mehak Dhaliwal, Rasta Tadayon, Andong Hua +2Large Language Model UncertaintyLarge Language Model Reinforcement Learning

    University of California, Santa Barbara

  33. Critic Experience Bank: Self-Evolving Step-Level Confidence Estimation for LLM Agents

    Jul 14, 2026Yaopei Zeng, Congchao Wang, JianHang Chen +3Large Language Model AgentsConfidence Estimation

    Pennsylvania State University · Virginia Tech · Purdue University +1

  34. Actor as Its Own Critic: Unifying Region Understanding and Localization via CycleGRPO

    Jul 13, 2026Xin Zhang, Haochen Wang, Yikang Zhou +3Multimodal Large Language ModelsLocalization

    National University of Singapore · ByteDance

  35. Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning

    Jul 1, 2026Konstantin GarbersSoft Actor-CriticCritic

    Peking University

  36. When LLMs Read Tables Carelessly: Measuring and Reducing Data Referencing Errors

    Jun 30, 2026Yuqing Yang, Qi Zhu, Zhen Han +5LLM Reasoning StrategiesCritic

    University of Southern California · AWS AI Labs

  37. The Inattentional Gap: Task-Conditioned Language and Vision Models Omit the Safety-Critical Signals They Can Otherwise Report

    Jun 25, 2026Kwan Soo Shin, In Seok Kang, Yunkyung Min +2Artificial Intelligence SafetyVision Foundation Models

    PolymathMinds Lab, Seoul, Republic of Korea · Department of Chemical Engineering, Pohang University of Science and Technology (POSTECH), Pohang, Republic of Korea · aSSIST University (Seoul School of Integrated Sciences & Technologies), Seoul, Republic of Korea +3

  38. Learning with a Single Rollout via Monte Carlo Pass@k Critic

    Jun 24, 2026Fengdi Che, Yang Liu, Lei Yu +4Large Language Model Reinforcement LearningCredit Assignment

    University of Alberta · BIGAI · University of Toronto +4

  39. Steer, Don't Solve: Training Small Critic Models for Large Code Agents

    Jun 20, 2026Shubham Gandhi, Yiqing Xie, Atharva Naik +2Coding AgentsCritic

    Carnegie Mellon University

  40. InterleaveThinker: Reinforcing Agentic Interleaved Generation

    Jun 11, 2026Dian Zheng, Harry Lee, Manyuan Zhang +4Multi-Reference Image GenerationImage Generation

    1CUHK MMLab · 2Meituan · 3CUHK IMIXR

  41. A History-Aware Visually Grounded Critic for Computer Use Agents

    Jun 9, 2026Jaewoo Lee, Zaid Khan, Archiki Prasad +7Computer-Use AgentsCritic

    University of North Carolina at Chapel Hill1 · Capital One2 · University of Texas at Austin3

  42. Noisy memory encoding explains negative polarity illusions

    Jun 3, 2026Yuhan Zhang, Edward GibsonNegationSurprisal

    Department of Linguistics, Stanford University · BIO-X Interdisciplinary Biosciences Institute, Stanford University · Department of Brain and Cognitive Sciences, Massachusetts Institute of Technology

  43. When Helping Hurts and How to Fix It: Multi-Agent Debate for Data Cleaning

    Jun 1, 2026Chirag Parmar, Akshat Mehta, Henglin Wu +2Multi-Agent DebateDebate

    1Meta Platforms, Inc.

  44. Critic-R: Improving Agentic Search using Instruction-tuned Retrievers with Natural Language Introspective Feedback

    May 30, 2026Md Zarif Ul Alam, Alireza Salemi, Hamed ZamaniAgentic SearchRetrievers

    Center for Intelligent Information Retrieval University of Massachusetts Amherst United States

  45. Weak Critics Make Strong Learners: On-Policy Critique Distillation for Scalable Oversight

    May 29, 2026Can Jin, Jiakang Li, Rui Wu +2Efficient On-Policy DistillationScalable Oversight

    Department of Computer Science, Rutgers University, Piscataway, United States.

  46. Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance

    May 28, 2026Shutong Ding, Zejia Zhong, Zhongyi Wang +4Diffusion-Based Reinforcement Learning MethodsAction Generation

    1ShanghaiTech University.

  47. CRITIC-R1: Learning Structured Critics for Retrieval-Augmented Generation

    May 28, 2026Wenhan Xiao, Ziwei Zhang, Chuanyue Yu +4Agentic Retrieval-Augmented Generation SystemsSearch-Augmented Reasoning

    Nankai University · Beihang University · Guangxi Normal University

  48. Explicit Critic Guidance for Aligning Diffusion Models

    May 26, 2026Zhengyang Liang, Qihang Zhang, Ceyuan YangDiffusion AlignmentDiffusion-Based Reinforcement Learning Methods

    University of Toronto · Vector Institute · The Chinese University of Hong Kong

  49. RL with Learnable Textual Feedback: A Bilevel Approach

    May 23, 2026Utsav Singh, Sidhaarth Sredharan, Souradip Chakraborty +1LLM Reasoning StrategiesFeedback

    University of Central Florida · 2Carnegie Mellon University · 3Universtiy of Maryland

  50. Don't Forget the Critic: Value-Based Data Rehearsal for Multi-Cyclic Continual Reinforcement Learning

    May 21, 2026Benjamin Poole, Andrew Quinn, Li Yang +1Offline Reinforcement LearningCatastrophic Forgetting

    Department of Computer Science University of North Carolina at Charlotte

  51. FedCritic: Serverless Federated Critic Learning-based Resource Allocation for Multi-Cell OFDMA in 6G

    May 20, 2026Amin Farajzadeh, Melike Erol-KantarciOrthogonal Frequency-Division MultiplexingOpen Radio Access Networks

    School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, Canada

  52. When Critics Disagree: Adaptive Reward Poisoning Attacks in RIS-Aided Wireless Control System

    May 19, 2026Deemah H. Tashman, Soumaya CherkaouiWireless CommunicationsLearning-Based Control

    Department of Computer and Software Engineering, Polytechnique Montreal, Montreal, Canada

  53. Inline Critic Steers Image Editing

    May 12, 2026Weitai Kang, Xiaohang Zhan, Yizhou Wang +4Image EditingMulti-Reference Image Generation

    University of Illinois Chicago · Adobe

  54. TOPPO: Rethinking PPO for Multi-Task Reinforcement Learning with Critic Balancing

    May 12, 2026Yuanpeng Li, Gefei Lin, Annie Qu +1Multi-Turn Reinforcement LearningProximal Policy Optimization

    UC Irvine · George Washington University · UC Santa Barbara +1

  55. ReCrit: Transition-Aware Reinforcement Learning for Scientific Critic Reasoning

    May 11, 2026Wanghan Xu, Yuhao Zhou, Hengyuan Zhao +8CriticLarge Language Model Reinforcement Learning

    Shanghai Jiao Tong University · Shanghai Artificial Intelligence Laboratory · This work was done during his internship at Shanghai Artificial Intelligence Laboratory. +4

  56. Judge, Then Drive: A Critic-Centric Vision Language Action Framework for Autonomous Driving

    Apr 30, 2026Lijin Yang, Jianing Huang, Zhongzhan Huang +2Autonomous DrivingHuman Driving

    Bosch Research

  57. EVPO: Explained Variance Policy Optimization for Adaptive Critic Utilization in LLM Post-Training

    Apr 21, 2026Chengjun Pan, Shichun Liu, Jiahang Lin +10Frictive Policy OptimizationCritic

    Peking University · Fudan University · Shanghai AI Lab +1

  58. Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning

    Apr 21, 2026Yuan Zhuang, Yuexin Bian, Sihong He +7Critic LearningOff-Policy Learning

    University of Connecticut · University of California San Diego · University of Texas at Arlington +1