Improvement

Ask about this topic

Momentum

16 papers in the last four weeks, up 78% on the four weeks before. 0.2% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 68

All topics
CardsList

  1. Towards Optimal Policy Improvement

    Oct 1, 2026Yaniv Oren, Viliam Vadocz, Wiktor Zabka +7Boltzmann PoliciesMarkov Decision Processes

    Department of Intelligent Systems, TU Delft · Centrum Wiskunde & Informatica, Amsterdam · Department of Computer Science, ETH Zürich +3

  2. Learning from Research: Toward Lifelong Agent Harness Evolution

    Sep 30, 2026Jingbo Yang, Kwei-Herng Lai, Xiaowen Wang +3Self-Evolving AgentsImprovement

    University of California, Santa Barbara · Microsoft

  3. From Solo to Social Learning: Characterizing Recursive Social Improvement in LLMs

    Sep 29, 2026Kunal Jha, Max Kleiman-Weiner, Natasha JaquesSelf-Improving AgentsLarge Language Model Agents

    Department of Computer Science, University of Washington, Seattle, WA 98195, USA.

  4. Skill-Space Shooting for Autonomous Robot Policy Improvement

    Sep 29, 2026Zihang Rui, Renhao Wang, Haoxu Huang +1Self-Improving AgentsRobot Systems

    Tsinghua University · UC Berkeley · Shanghai Qi Zhi Institute

  5. RSI-Master: Structuring Experiments to Guide Autonomous Model Improvement

    Sep 28, 2026Yaxin Du, Xiyuan Yang, Zhifan Zhou +10Recursive Self-ImprovementArtificial Intelligence Research

    Shanghai Jiao Tong University · Carnegie Mellon University · University of Waterloo

  6. From internal representations to model improvement through prediction errors

    Sep 28, 2026Yushi Nakaya, Kenichi Higuchi, Shuichi IshidaPrediction ErrorRarity

    Adansons Corp., 214 Homer Ave, Palo Alto, 94301, CA, USA. · Tohoku University, 6-6-11-803 Aza-Aoba Aramaki, Aoba-ku, Sendai, 980-8579, Miyagi, Japan.

  7. Audit the Scaffold, Not the Checkpoint: A Stationarity Dichotomy for Recursive Self-Improvement in Agentic Coding

    Sep 28, 2026Sebastian Bobadilla-Suarez, Bob Suh, Ryan FortinScaffoldsCoding Agents

    OnCorps

  8. NLPG: Natural-Language Policy Gradients for Self-Evolving Language Agents

    Sep 27, 2026Xu Liu, WenZhang Wei, Jun Cao +4Large Language Model Policy OptimizationImprovement

    School of Electronic Information, Wuhan University, Wuhan 430079, China · School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China · State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan 430079, China

  9. SWE-Prometheus: Measuring Engineering Governance Improvements in Real-World Repositories

    Sep 24, 2026Jiajun Wu, Leixin Sun, Zihan Tan +9Repository-Level Code UnderstandingGovernance

    CosmosMind · ModCraft · Peking University +2

  10. MIRCID: Inferred Hub-miRNAs Drive Cross-Task Improvements in Drug Mechanistic Modeling

    Sep 18, 2026Xin Cao, Yigang Chen, Jiatong Xu +11TranscriptomicsImprovement

    School of Medicine, The Chinese University of Hong Kong, Shenzhen, Longgang District, Shenzhen, Guangdong 518172, China · School of Data Science, The Chinese University of Hong Kong, Shenzhen, Longgang District, Shenzhen, Guangdong 518172, China · Warshel Institute for Computational Biology, School of Medicine, The Chinese University of Hong Kong, Shenzhen, Longgang District, Shenzhen, Guangdong 518172, China +2

  11. Model-Agnostic and Language-Agnostic Voice Pipeline Improvement for the Agriculture Domain

    Sep 17, 2026Aakash Singh, Lakshmi Pedapudi, Chandrashekar M S +3End-To-End Automatic Speech Recognition ModelsTranscript

    Digital Green

  12. CARE-VI: Conservative Adaptive Reliability Estimation for Value Improvement in Off-Policy Actor-Critic Learning

    Sep 17, 2026Xiang Zou, Shengzhu Shi, Junqi Gao +1Soft Actor-CriticTemporal Difference

    School of Mathematics, Harbin Institute of Technology, Harbin 150001, China

  13. Data-Efficient Language Modeling: From Frontier Advancement to Principle-Guided Model Improvement

    Sep 12, 2026Shuxing Yang, Kaihao Zhu, Junjie Yang +13Frontier ModelsFrontiers

    College of Information Science and Electronic Engineering, Zhejiang University · Qiushi Engine Team

  14. Emergency Department Revisit Quality Review Screening: Exploring Human Decision-Making and Artificial Intelligence Support

    Sep 9, 2026Jonathan A. Handler, Marlene I. Robles-Granda, Jacob E. Mefford +5Clinician TrustEmergency Departments

    Clinical Intelligence and Advanced Data Lab, OSF HealthCare, Peoria, IL · Digital Innovation Development, OSF HealthCare, Peoria, IL · OnCall, OSF HealthCare, Peoria, IL +7

  15. A Sharp Barrier for Consistent Submodular Maximization: Any Improvement over 2−22-\sqrt{2} Entails Exponential Queries or Linear Recourse

    Sep 9, 2026Shi Fu, Qixin Zhang, Dacheng TaoSubmodular FunctionsFirst Order Oracle Complexity

    Nanyang Technological University, Singapore

  16. Evaluating and Improving Evidence-Grounded Fact-Checking in LLMs via Multi-Round Evidence Ablation

    Sep 8, 2026Xingyu Deng, Mingzi Cao, Nikolaos Aletras +2Fact-CheckingLarge Language Model Reliability

    University of Sheffield · Sheffield, UK

  17. OBER+: Continuity-Aware Reporting and Traceable Continuous Improvement in Outcome-Based Education

    Sep 3, 2026Elakkiya RajasekarInstitutionsCurriculum

    Department of Computer Science, Birla Institute of Technology and Science Pilani, Dubai Campus, Dubai, United Arab Emirates

  18. OCR-EDR: Rendering-Aware Diagnosis and Repair for Closed-Loop OCR Improvement

    Sep 3, 2026Linnan Zhao, Kang Liu, Hao Yu +3Optical Character RecognitionRepair

    Wechat Vision, Tencent

  19. Harness-of-Harness: Multi-Day Autonomous Software Development with Continual Improvement

    Sep 1, 2026Haoyang Yan, Min-le Su, Hangfan Zhang +6Self-Improving AgentsCoding Agents

    Shanghai Artificial Intelligence Laboratory

  20. LLM Post-Training as Brownfield Maintenance: An Industrial Perspective on Dataware Engineering

    Aug 31, 2026Gopi Krishnan Rajbahadur, Amir M. Ebrahimi, Boyuan Chen +1Post-TrainingTraining Data

    Queen’s University, Canada · Centre for Software Excellence, Huawei Technologies, Canada

  21. Self-Aware Active Learning Enables Continual Improvement in Autonomous Driving

    Aug 30, 2026Dong Hu, Chao Huang, Carman K. M. Lee +1Autonomous DrivingPool-Based Active Learning

    Department of Industrial and Systems Engineering, The Hong Kong Polytechnic University, Hong Kong · School of Electrical and Mechanical Engineering, Adelaide University, Australia · Department of Computer Science, University College London, United Kingdom

  22. LLM-Guided Graph Generation for Structure-Based Local Improvement Methods

    Aug 13, 2026Hai Xia, Vaidyanathan Peruvemba Ramaswamy, Stefan SzeiderLarge Neighborhood SearchData Generation

    Algorithms and Complexity Group, TU Wien, Austria

  23. Numeracy in Large Language Models: Fundamental Limitations and Paths to Improvement

    Aug 13, 2026Aoxin NiMathematical Reasoning BenchmarksFundamental Limits

    Department of Computer Science University of Chinese Academy of Sciences

  24. Expert-Guided g-computation with Large Language Models for Estimating Causal Effects on Timings: Applications to Hospital Quality Improvement

    Aug 11, 2026Patrick Vossler, Jialin Ouyang, F. Richard Guo +5Patient TrajectoriesImprovement

    University of California, San Francisco · University of Michigan, Ann Arbor · University of Washington, Seattle

  25. Rethinking Self-Evolving Agents: Do We Still Need Prescribed Optimization Pipelines?

    Aug 10, 2026Hui Xue, Fan YangSelf-Evolving AgentsPrompt Optimization

    Microsoft Research

  26. Shaping Human-AI Interactions to Provide Improvement Pathways and Balance Competing Objectives

    Aug 6, 2026Keziah NaggitaHuman-Ai InteractionArtificial Intelligence Alignment

    TOYOTA TECHNOLOGICAL INSTITUTE AT CHICAGO Chicago, Illinois

  27. Improving Auto-Design of Neural PDE Solvers with a Domain-Specific Language

    Aug 5, 2026Shengxin Kong, Liwen Xu, Jingwen FuNeural Partial Differential Equation SolversEvolutionary Search

    School of Sciences, North China University of Technology, Beijing, China · Beijing Zhongguancun Academy, Beijing, China

  28. FinReportBench: Measuring and Improving Institution-Grade Financial Report Generation

    Aug 5, 2026Yinghao Tang, Tan Zhenwei, Yiyao Wang +4ReportModel Auditing

    State Key Laboratory of CAD&CG, Zhejiang University · Ant Group

  29. Continuous Improvement and Parallel Autonomous Exploration: An LLM-Agent Framework for Searching Large Solution Spaces

    Aug 5, 2026Dulmini Hettiarachchi, Andre Rusli, Julio Christian Young +1Large Language Model AgentsExploration

    Mercari, Inc. Japan

  30. Simple-regret rates and minimax optimality of fixed-prior expected improvement in Matérn and squared-exponential RKHSs

    Jul 31, 2026Emmanuel Vazquez, Sébastien PetitReproducing Kernel Hilbert SpacesMinimax Rate

    Université Paris-Saclay, CNRS, CentraleSupélec, Laboratoire des Signaux et Systèmes, 91190 Gif-sur-Yvette, France · Laboratoire national de métrologie et d’essais (LNE), 1 rue Gaston Boissier, 75724 Paris Cedex 15, France

  31. ClawTrack: Towards Trace-Level Evaluation and Improvement of Real-World Autonomous Agents

    Jul 30, 2026Xingjian Wu, Xuhang Zhu, Xingchen Liu +6Autonomous AgentsClaw-Like Agent

    Meituan

  32. SWE-NFI: Studying and Benchmarking Coding Agents for Non-Functional Improvements

    Jul 29, 2026Pengyu Xue, He Yang Yuan, Xin Wang +6Coding AgentsAgentic Benchmarks

    York University Toronto, Ontario, Canada · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, Guangdong, China · Singapore Management University Singapore, Singapore +2

  33. Teach it to stop, not just to click

    Jul 19, 2026Barada Sahu, Shivesh PandeyAgenticImprovement

    Cabal AI · Para AI

  34. Evaluating Neural Decompilation of Dart AOT Binaries: Fine-Tuning, Metric Validity, Specification Leakage, and Reliability

    Jul 7, 2026Raafat Abualazm, Ayman AboElhassan, Amr G. WassalModel Fine-TuningHuman-Annotated Benchmark

    Cairo University, Computer Engineering Department, Faculty of Engineering, Giza, Egypt

  35. Profit-Based Counterfactual Explanations for Product Improvement: A Case Study of Manga Sales in Japan

    Jul 2, 2026Keita Kinjo, Takeshi EbinaCounterfactual ExplanationShapley Additive Explanations

    Faculty of Business Studies, Kyoritsu Women’s University, 2-2-1, Hitotsubashi, Chiyoda-ku, Tokyo, 101-8437, Japan · School of Commerce, Meiji University, 1-1, Kanda-surugadai, Chiyoda-ku, Tokyo, 101-8301, Japan

  36. What Drives Interactive Improvement from Feedback?

    Jun 29, 2026Bartłomiej Cupiał, Jan Łojek, Mikołaj Garstecki +3FeedbackReinforcement Learning From Human Feedback

    University of Warsaw · AKCES NCBR · Princeton University +2

  37. Improved Large Language Diffusion Models

    Jun 24, 2026Shen Nie, Qiyang Min, Shaoxuan Xu +7Diffusion Language ModelsDiffusion Models

    Gaoling School of Artificial Intelligence, Renmin University of China · Beijing Key Laboratory of Research on Large Models and Intelligent Governance · Engineering Research Center of Next-Generation Intelligent Search and Recommendation, MOE +1

  38. Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements

    Jun 22, 2026Jingjie Ning, Xiaochuan Li, Ji Zeng +2Molecular Property PredictionMoleculenet

    School of Computer Science, Carnegie Mellon University, Pittsburgh, Pennsylvania, USA. · DP Technology, Beijing, China.

  39. LOKI: Memory-Free Null-Space Constrained Lifelong Knowledge Editing

    Jun 18, 2026Masih Eskandar, Miquel Sirera Perelló, Stratis Ioannidis +1Multimodal Knowledge EditingLarge Language Model Memory

    Department of Electrical and Computer Engineering Northeastern University Boston, MA, 02115

  40. The Illusion of Improvement: Reject Inference Strategies in Credit Scoring

    Jun 16, 2026Bruno Scarone, Ricardo Baeza-YatesRejectionSelection Bias

    Northeastern University, Boston, MA, USA · KTH Royal Institute of Technology, Stockholm, Sweden

  41. Visual Verification Enables Inference-time Steering and Autonomous Policy Improvement

    Jun 16, 2026Mingtong Zhang, Dhruv ShahRobot PoliciesInference-Time Steering

    Princeton University

  42. OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics

    Jun 8, 2026Mingxian Lin, Shengju Qian, Yuqi Liu +9Agentic BenchmarksWebarena Domains

    1The University of Hong Kong · 2LIGHTSPEED · 3The Chinese University of Hong Kong +1

  43. PACE: Anytime-Valid Acceptance Tests for Self-Evolving Agents

    Jun 6, 2026Zayx ShawnSelf-Evolving AgentsSelf-Evolution

    Independent Researcher

  44. Coherent Off-Policy Improvement of Large Behavior Models with Learned Rewards

    Jun 1, 2026Christian Scherer, Joe Watson, Theo Gruner +3Reinforcement Fine-TuningDexterous Manipulation

    Technical University of Darmstadt · Zuse School ELIZA · University of Oxford +2

  45. Improvise, Adapt, Overcome: An On-The-Fly Multifidelity Algorithm for Efficient Machine Learning

    Jun 1, 2026Vivin Vinod, Peter ZaspelQuantum ChemistryMulti-Fidelity

    School of Mathematics and Natural Sciences, University of Wuppertal, Germany.

  46. Linear Strategic Classification with Endogenous Improvements

    May 31, 2026Siddharth Shrivastava, Mahvith Akshintala, B Vamsha Vardhan Reddy +3ClassifierImprovement

    Department of Artificial Intelligence IIT Hyderabad · IIIT Hyderabad · DepartementIITofHyderabadArtifical Intelligence

  47. StressDream: Steering Video World Models for Robust Policy Evaluation and Improvement

    May 29, 2026Junwon Seo, Sushant Veer, Ran Tian +6Video World ModelsDream

    Carnegie Mellon University · NVIDIA Research · University of Washington +1

  48. Welfare, Improvability, and Variance: A Principal-Agent Approach to Optimal Benchmark Item Aggregation

    May 29, 2026Andreas Haupt, Justin Hartenstein, Anka Reuel +2WelfareAgentic Benchmarks

    Institute for Computational and Mathematical Engineering Stanford University · Department of Computer Science Stanford University

  49. CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning

    May 27, 2026Linas Nasvytis, Simon Jerome Han, Ben Prystawski +3Contrastive LearningImprovement

    Stanford University

  50. ImProver 2: Iteratively Self-Improving LMs for Neurosymbolic Proof Optimization

    May 21, 2026Riyaz Ahuja, Tate Rowney, Jeremy Avigad +1Theorem ProvingNeuro-Symbolic Framework

    Carnegie Mellon University

  51. PROTEA: Offline Evaluation and Iterative Refinement for Multi-Agent LLM Workflows

    May 18, 2026Kazuki Kawamura, Satoshi Waki, Kei TatenoLarge Language Model WorkflowsAgentic Workflow Design

    Sony Group Corporation

  52. Task Capability Improvement Algorithm for Collaborative Manipulators

    May 17, 2026Keshab Patra, Arpita Sinha, Anirban GuhaImprovementTransport

    Department of Mechanical Engineering, Indian Institute of Technology Bombay, Mumbai, Maharashtra, India · Center for Systems and Control, Indian Institute of Technology Bombay, Mumbai, Maharashtra, India

  53. 4DVGGT-D: 4D Visual Geometry Transformer with Improved Dynamic Depth Estimation

    May 12, 2026Ying Zang, Xuanyi Liu, Yidong Han +94D ReconstructionVisual Geometry Grounded Transformer

    4Huzhou University · 2Peking University · 1KOKONI 3D, Moxin Technology +4

  54. Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data

    May 11, 2026Ahmed Mehdi Inane, Vincent Quirion, Gintare Karolina Dziugaite +1Unlearning MethodMembership Inference Attacks

    Universit´e de Montr´eal · Mila, Quebec AI Institute · Google DeepMind

  55. Improved Model-based Reinforcement Learning with Smooth Kernels

    May 8, 2026Kun Long, Yuqiang Li, Xianyi WuModel-Based Reinforcement LearningOffline Reinforcement Learning

    School of Statistics, KLATASDS-MOE, East China Normal University, North Zhongshan Road, Shanghai, 200062, PR China.

  56. Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems

    May 7, 2026Sicheng Ma, Tianyue Yang, Xiuzhe Wu +1High-FidelityReconstruction Fidelity

    Department of Physics University of Cambridge · The Center for Computational Science University College London · Department of Computer Science University College London

  57. Leveraging Code Automorphisms for Improved Syndrome-Based Neural Decoding

    May 5, 2026Raphaël Le Bidan, Ahmad Ismail, Elsa Dupraz +1Neural CodecsImprovement

    IMT Atlantique, Lab-STICC UMR CNRS 6285, Brest, France

  58. Conformalized Percentile Interval: Finite Sample Validity and Improved Conditional Performance

    May 4, 2026Ran Zou, Wanrong Zhu, Bin NanConditional DistributionFinite-Sample

    Department of Statistics, University of California, Irvine

  59. From Fuzzy to Formal: Scaling Hospital Quality Improvement with AI

    Apr 21, 2026Patrick Vossler, Jean Feng, Venkat Sivaraman +9Qualitative ResearchImprovement

    University of California, San Francisco · 2Zuckerberg San Francisco General Hospital

  60. Improvements to the post-processing of weather forecasts using machine learning and feature selection

    Apr 21, 2026Kazuma Iwase, Tomoyuki TakenawaPrecipitation NowcastingPost-Processing

    Graduate School of Marine Science and Technology, Tokyo University of Marine Science and Technology, 2-1-6 Etchujima, Koto-ku, Tokyo 135-8533, Japan