Process-Level Supervision

Ask about this topic

Momentum

33 papers in the last four weeks, up 200% on the four weeks before. 0.3% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 154

All topics
CardsList

  1. Progress Reward Modeling for Robotic Learning: A Comprehensive Survey

    Jul 22, 2026Jianshu Zhang, Keliang Wu, Haoran Lu +8Progress Reward ModelingScalable Robot Learning

    Northwestern University · Carnegie Mellon University · University of Wisconsin–Madison +2

  2. Scalable Low-Cost Laboratory Automation: A Digital Twin-Integrated Robotic Platform for Autonomous Liquid Handling (RAINBOT)

    Jul 22, 2026Mohamed Rami Ayeche, Souhil Sid, Ahyen Mostofa +3LaboratoryRobocasa

    Acceleration Consortium, University of Toronto, Toronto, Canada. · AISCIA Informatics, Qatar Science and Technology Park, Doha, Qatar · Hamad Bin Khalifa University (HBKU), Education City, Doha, Qatar.

  3. MOF-Sleuth: Tool-Grounded Reward Alignment for Explainable Fine-Grained MOF CIF Auditing

    Jul 22, 2026Yu Liu, Zhiwei Yang, Diandian Guo +7Chemical StructuresMllm-Based

    Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, Beijing, China · Beijing University of Posts and Telecommunications, Beijing, China +2

  4. Extending a Large View Synthesis Model for Multi-view Panoptic Segmentation

    Jul 22, 2026Kwonyoung Ryu, In-Jae Lee, Jonghyun Jin +3Panoptic SegmentationNovel View Synthesis

    POSTECH · Seoul National University · POSCO DX +1

  5. DAIS: Dependency-Aware Intermediate QA Supervision for Complex Reasoning

    Jul 21, 2026Yu Wang, Ming Fan, Xicheng Zhang +5Process-Level SupervisionNatural Language Inference

    1Xi’an Jiaotong University · 2Huawei Technologies Ltd.

  6. Step-Level Preference Learning for Generative Agents in Social Simulations

    Jul 16, 2026Wenchang Gao, Pingyue Sheng, Lanlan Qiu +7Preference LearningSimulation-Based Reinforcement Learning

    Shanghai Qi Zhi Institute · Tsinghua University · Xiongan AI Institute +3

  7. RainDancer: RGB-Event Video Deraining with Rain-Oriented Spiking Dynamics

    Jul 15, 2026Kui Jiang, Runzhe Li, Zhaocheng Yu +3RgbtVideo Restoration

    School of Computer Science and Technology, Harbin Institute of Technology, Harbin, China · School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China

  8. LOTAPO: Leave-One-Turn Attribution for Self-Generated Process Rewards in Multi-Turn Search Reasoning

    Jul 15, 2026Qiang Zhu, Jiajun Wu, Longyi WangProcess Reward ModelProcess-Level Supervision

    Zhejiang University

  9. When Rubrics Change: Cross-Rubric Generalization for Critical Thinking Essay Scoring

    Jul 15, 2026Nischal Ashok Kumar, Payu Wittawatolarn, Sana Kang +7Automated Essay ScoringTask-Specific Rubrics

    University of Massachusetts Amherst, United States · University of Minnesota, United States · Brighter Research, United States +3

  10. EasyOPD: An Easy-to-use On-Policy Distillation Framework for Large Language Models

    Jul 13, 2026Jie Sun, Mao Zheng, Mingyang Song +7Efficient On-Policy DistillationRp-Opsd

    University of Science and Technology of China · Shanghai Innovation Institute · LLM Department, Tencent +1

  11. SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation

    Jul 9, 2026Sijia Gu, Noor Nashid, Ali MesbahTest GenerationCoding Agents

    University of British Columbia Vancouver, Canada

  12. Ensemble Diversity Optimization for Subjective Supervision

    Jul 9, 2026Xia Cui, Ziyi Huang, N. R. AbeynayakeEnsembleCross-Entropy Losses

    School of Computing and Mathematics, Manchester Metropolitan University, Manchester, UK. · School of Computer Science, Hubei University, Wuhan, China.

  13. VSRo-200: A Romanian Visual Speech Recognition Dataset for Studying Supervision and Multimodal Robustness

    Jul 9, 2026Iulia-Maria Udrea, Alexandra Diaconu, Bogdan AlexeHigh Confidence Pseudo-LabelsVideo Dataset

    Department of Computer Science, University of Bucharest

  14. HELP: Human-Efficient Large-Scale Robot Post-Training with Rollout Segmentation

    Jul 8, 2026Shaopeng Zhai, Qi Zhang, Tianyi Zhang +5Humanoid RoboticsRollout

    Continuous Learning Team, Shanghai AI Laboratory

  15. What You See Is What You Get: Observation-Aligned Supervision for Chart-to-Code Generation

    Jul 6, 2026Tianhao Niu, Qingfu Zhu, Wanxiang CheImage-To-Code GenerationCode Generation

    Research Center for Social Computing and Interactive Robotics Harbin Institute of Technology, China

  16. KARMA: Knowledge graph-based Automated Reasoning Materialization and Alignment

    Jul 3, 2026Jinkyeong Choi, Chaebin Jeong, Donghyeon ParkHierarchical Semantic AlignmentContrastive Learning

    Sejong University

  17. Reward Granularity in RLVR: Comparing Process and Outcome Reward Structures for Mathematical Reasoning in Small Language Models

    Jul 3, 2026Anagha Radhakrishna Palandye, Rebecca Glick, Osheen KaulReinforcement Learning With Verifiable RewardReward Signal

    New York University

  18. Evo-PI: Aligning Medical Reasoning via Evolving Principle-Guided Supervision

    Jun 30, 2026Xianda Zheng, Huan Gao, Meng-Fen Chiang +3LLM Reasoning StrategiesClinical Reasoning Training

    School of Computer Science, University of Auckland · Sapiens · National Yang Ming Chiao Tung University +3

  19. Training Vision-Language-Action Models with Dense Embodied Chain-of-Thought Supervision

    Jun 29, 2026Haoyang Li, Guanlin Li, Youhe Feng +9Diffusion-Based Vision-Language-ActionsCross-Embodiment Transfer

    1Renmin University of China · 2Zhipu AI

  20. StrucTab: A Structured Optimization Framework for Table Parsing

    Jun 29, 2026Gengluo Li, Shangpin Peng, Chengquan Zhang +10Document ParsingStructure-Aware

    Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China · School of Cyber Security, University of Chinese Academy of Sciences, China · LLM Department, Tencent, China +3

  21. Do Models Read What They Write? Causal Registers in Scratchpad Reasoning

    Jun 28, 2026Benjamin Shih, John Winnicki, Eric DarveProcess-Level SupervisionCausal

    Institute for Computational and Mathematical Engineering Stanford University

  22. The Weakest Link Tells It All: Outcome-Supervised Process Reward Modeling via Learnable Credit Assignment

    Jun 26, 2026Tianyu Jia, Yue Fang, Hongxin Ding +6Process Reward ModelCredit Assignment

    National Engineering Research Center of Software Engineering, Peking University, Beijing, China · School of Computer Science, Peking University, Beijing, China · Key Laboratory of High Confidence Software Technologies, Ministry of Education, Beijing, China +3

  23. Scaling Laws for Task-Specific LLM Distillation

    Jun 23, 2026Lavinia Ghita, Dhruv Desai, Ioana BoierLarge Language Model CompressionDataset Distillation

    NVIDIA

  24. Dense Reward for Multi-View 3D Reasoning with Global Maps and Local Views

    Jun 22, 2026Jiho Choi, Seonho Lee, Seojeong Park +13D RepresentationVisual Grounding Benchmarks

    Graduate School of Artificial Intelligence, KAIST, Republic of Korea · KRAFTON, Republic of Korea

  25. Quality and Agreement in Multilabel Emotion Annotation: A Case Study and Evaluation Framework

    Jun 19, 2026Emily Öhman, Anna KoufakouEmotion RecognitionMulti-Label Classification

    Waseda University, Tokyo, Japan · Florida Gulf Coast University, Fort Myers FL, USA

  26. Mind the Privileged-to-Camera Gap: Actor-Centric Sidecar Supervision for Camera-First Open-Loop Waypoint Prediction

    Jun 18, 2026Feeza Khan Khanzada, Jaerock KwonWaypointsPhotometric Supervision

    Department of Electrical and Computer Engineering, University of Michigan-Dearborn, 4901 Evergreen Rd, Dearborn, MI 48128, United States

  27. What Makes Effective Supervision in Latent Chain-of-Thought: An Information-Theoretic Analysis

    Jun 18, 2026Xinghao Chen, Chak Tou Leong, Wenjin Guo +3Efficient Latent ReasoningChain-of-Thought Reasoning

    Ningbo Institute of Digital Twin, Eastern Institute of Technology, Ningbo, China · Department of Computing, The Hong Kong Polytechnic University, Hong Kong, China.

  28. Quantifying and Auditing LLM Evaluation via Positive--Unlabeled Learning

    Jun 17, 2026Zilong Zhang, Yi-Ting Hung, Lei Ding +1Large Language Model EvaluationPositive--Unlabeled Learning

    Department of Mathematics and Statistics Georgia State University · Department of Statistics University of Manitoba

  29. APT: Atomic Physical Transitions for Causal Video-Language Understanding

    Jun 17, 2026Shang Wu, Haoran Lu, Songling Liu +6Sharp TransitionsTransitions

    Northwestern University · Dolby Laboratories

  30. EnvRL: Learn from Environment Dynamics in Agentic Reinforcement Learning

    Jun 16, 2026Zhitong Wang, Songze Li, Hao Peng +4Agentic Reinforcement LearningLong-Horizon Agents

    Department of Computer Science and Technology, Tsinghua University · Shanghai AI Laboratory

  31. DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents

    Jun 15, 2026Minghang Zhu, Chuyang Wei, Junhao Xu +3Process-Level SupervisionOffline Reinforcement Learning

    Shandong University, Qingdao, China · Zhongguancun Academy, Beijing, China · Fudan University, Shanghai, China

  32. Scaling LLM Reasoning from Minimal Labels: A Semi-Supervised Framework with a Lightweight Verifier

    Jun 15, 2026Keizo Kato, Chenhui Chu, Yugo Murawaki +1LLM Reasoning StrategiesProcess-Level Supervision

    Fujitsu Limited, Kawasaki, Japan · Kyoto University, Kyoto, Japan · National Institute of Informatics, Tokyo, Japan

  33. Adapting Reinforcement Learning with Chain-of-Thought Supervision for Explainable Detection of Hateful and Propagandistic Memes

    Jun 13, 2026Mohamed Bayan Kmainasi, Mucahid Kutlu, Ali Ezzat Shahroor +2MemesMultimodal Large Language Models

    Qatar Computing Research Institute, Doha, Qatar · Qatar University, Doha, Qatar · APAVI.AI, France +1

  34. Multimodal Graph Negative Learning

    Jun 11, 2026Zhengyu Wu, Xu Wang, Hongchao Qin +4Multimodal LearningProcess-Level Supervision

  35. Shared Semantics, Divergent Mechanisms: Unsupervised Feature Discovery by Aligning Semantics and Mechanisms

    Jun 6, 2026Hyunjin Cho, Youngji Roh, Jaehyung KimMechanistic InterpretabilityInterpretability

    Yonsei University

  36. From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning

    Jun 5, 2026Yuhang Zhou, Yixin Cao, Guangnan YeLLM Reasoning StrategiesProcess Reward Model

    Fudan University · Shanghai Innovation Institute

  37. When Evidence is Sparse: Weakly Supervised Early Failure Alerting in Dialogs and LLM-Agent Trajectories

    Jun 3, 2026Avinash Baidya, Xinran Liang, Ruocheng Guo +2Early Failure PredictionEarly Warning

    1Intuit AI Research · 2Princeton University

  38. Self-supervised User Profile Generation for Personalization

    Jun 3, 2026Clark Mingxuan Ju, Yuwei Qiu, Tong Zhao +1Large Language Model PersonalizationProfile

    Snap Inc. · Bellevue, WA USA

  39. Scaling Self-Evolving Agents via Parametric Memory

    Jun 3, 2026Tao Ren, Weiyao Luo, Hui Yang +8Parametric MemorySelf-Evolving Agents

    Qwen-Character Team · Alibaba Group · Peking University

  40. Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots

    Jun 3, 2026Guangcheng Zhu, Shenzhi Yang, Haobo Wang +7Reinforcement Learning With Verifiable RewardVerifiable Rewards

    1Zhejiang University · 2Ant Group

  41. DSIRM: Learning Query-Bridged Discrete Semantic Identifiers for E-commerce Relevance Modeling

    Jun 3, 2026Bokang Wang, Xing Fang, Mingmin Jin +4RelevanceProcess-Level Supervision

    Taobao & Tmall Group of Alibaba Hangzhou, China

  42. GeoSem-WAM: Geometry- and Semantic-Aware World Action Models

    Jun 2, 2026Fulong Ma, Daojie Peng, Wenjun Yue +4Efficient World-Action ModelWorld Models

    HKUST(GZ) · OC · HKU +4

  43. From Long News to Accurate Forecast: Importance-Aware Fusion and PRM-Guided Reflection for Time Series Forecasting

    Jun 2, 2026Mingyang Liu, Qingcan Kang, Yuke Wang +6Large Language Model ForecastingTime Series Forecasting

    Department of Computer Science, City University of Hong Kong · Work done as an intern in Huawei Noah’s Ark Lab. · Huawei Noah’s Ark Lab

  44. EvoPool: Evolutionary Programmatic Annotation for Label-Efficient Specialized Supervision

    Jun 1, 2026Tianyi Xu, Yaolun Zhang, Xuan Ouyang +1Human AnnotatorsMulti-Agent Evolution

    Oregon State University · University of Wisconsin–Madison

  45. Semi-Supervised Hyperbolic Hierarchical Clustering with Set-Level Structural Priors

    Jun 1, 2026Junjing Zheng, Xinyu Zhang, Xiangfeng Qiu +2Semi-Supervised LearningClustering

    College of Electronic Science and Technology, National University of Defense Technology, Changsha 410073, China

  46. DASH: Dual-Branch Score Distillation for Guidance-Calibrated Compact Diffusion Models

    May 30, 2026Abdullah Al Shafi, Kazi Saeed Alam, Sk Imran Hossain +1Dataset DistillationText-Conditioned Diffusion Model

    Khulna University of Engineering & Technology, Bangladesh · University Clermont Auvergne, France

  47. COMPASS: Cognitive MCTS-Guided Process Alignment for Safe Search Agents

    May 29, 2026Wenkai Shen, Pengyang Zhou, Jiahe Xu +5Safety AlignmentSearch Agents

    Zhejiang University

  48. Reinforcement Learning with Robust Rubric Rewards

    May 28, 2026Ya-Qi Yu, Hao Wang, Fangyu Hong +15Reinforcement Learning With Verifiable RewardReference-Guided Multimodal In-Context Verification

    Huawei Technologies Co., Ltd.

  49. SCOPE: A Lightweight-training LLM Framework for Air Traffic Control Readback Monitoring

    May 28, 2026Qihan Deng, Minghua Zhang, Yang Yang +1Air Traffic ControlPilot

    Department of Mechanical and Aerospace Engineering, The Hong Kong University of Science and Technology, Clear Water Bay, 999077, Hong Kong · School of Electronic and Information Engineering, Beihang University, Beijing, 100191, China · State Key Laboratory of CNS/ATM, Beijing, 100191, China

  50. GTA: Generating Long-Horizon Tasks for Web Agents at Scale

    May 28, 2026Tenghao Huang, Kung-Hsiang Huang, Prafulla Kumar Choubey +4Web AgentsAgentic Benchmarks

    University of Southern California · Salesforce AI Research · University of California, Davis

  51. Human Label Variation as Stable Signal: Learning Annotator-Specific Explanation Behavior via Cross-Annotator Preference Optimization

    May 27, 2026Beiduo Chen, Pingjun Hong, Ziyun Zhang +3Human AnnotatorsProcess-Level Supervision

    U MaiNLP, Center for Information and Language Processing, LMU Munich, Germany · Æ Munich Center for Machine Learning (MCML), Munich, Germany · [ University of Vienna, Austria +1

  52. Activation Steering for Synthetic Data Generation: The Role of Diversity in Downstream Safety Detection

    May 27, 2026Vijeta Deshpande, Tootiya Giyahchi, Veena Padmanabhan +2Synthetic DataLinear Activation Steering

    UMass Lowell · Amazon · Amazon, CMU +1

  53. Better heads do not guarantee better binarized constituency parsing

    May 27, 2026Zeyao Qi, Yige Chen, Eitan Klinger +2Syntactic StructureDocument Segmentation

    The Chinese University of Hong Kong, Ma Liu Shui, Hong Kong · The University of British Columbia, Vancouver, Canada · Korea Advanced Institute of Science & Technology, Daejeon, South Korea

  54. ESC-Skills: Discovering and Self-Evolving Skills for Emotional Support Conversations

    May 27, 2026Jie Zhu, Huaixia Dou, Shuo Jiang +5Emotional Support Conversation TaskSkill Evolution

    School of Computer Science and Technology, Soochow University · 2Qwen DianJin Team, Alibaba Cloud Computing

  55. Quantifying Empirical Compute-Supervision Tradeoffs in RLVR

    May 24, 2026Ryo Mitsuhashi, Patrick Chen, Isabelle Tseng +2Reinforcement Learning With Verifiable RewardProcess-Level Supervision

    1Princeton University

  56. How to Steer Your Multi-Agent System: Human-LLM Collaborative Planning

    May 21, 2026Zeyu He, Hannah Kim, Dan Zhang +1Large Language Model PlanningProcess-Level Supervision

    Penn State University · Work done during internship at Megagon Labs · Megagon Labs

  57. REFLECTOR: Internalizing Step-wise Reflection against Indirect Jailbreak

    May 20, 2026Jiachen Ma, Jiawen Zhang, Xiangtian Li +3Jailbreak AttacksProcess-Level Supervision

    Fudan University · Shanghai Artificial Intelligence Laboratory · Zhejiang University

  58. Fast and Featureless Node Representation Learning with Partial Pairwise Supervision

    May 19, 2026Sujan Chakraborty, Saptarshi BejGraph Representation LearningGraph Neural Networks

    School of Data Science, Indian Institute of Science Education and Research, Thiruvananthapuram, 695551, Kerala, India

  59. LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward Decomposition

    May 19, 2026Yanyu Chen, Jiyue Jiang, Dianzhi Yu +8LLM Reasoning StrategiesEfficient Latent Reasoning

    The Chinese University of Hong Kong · Shanghai Jiaotong University · Fudan University

  60. OmniISR: A Unified Framework for Centralized and Federated Learning via Intermediate Supervision and Regularization

    May 19, 2026Wei-Bin Kou, Guangxu Zhu, Ming Tang +4Federated LearningIntelligent Edge

    Yinwang Intelligent Technology Co. Ltd., Shenzhen, China