Traces

Ask about this topic

Momentum

47 papers in the last four weeks, up 262% on the four weeks before. 0.5% of all new papers.

Jul 13Week of Sep 28
View on map

Latest papers 257

All topics
CardsList

  1. Does an Agent's History Tell You When Compaction Will Hurt? A Modest, Bounded Effect on the TRACE Paired-Replay Corpus

    Oct 6, 2026Egor Pakhomov, Erik NijkampTraces

    Salesforce AI Research

  2. TRACE: Tackling Real-World Resource Assignment Problems via Agentic Heuristic Design

    Oct 1, 2026Jose A. Ayala-Romero, Andres Garcia-Saavedra, Xavier Costa-PerezAutomated Heuristic DesignRepair-Assignment Problem

    NEC Laboratories Europe · i2CAT Foundation and ICREA

  3. Auditing Routing Entropy as an Uncertainty Signal in Attention-Residual Transformers

    Oct 1, 2026Wenhao Liang, Lin Yue, Wei Emma Zhang +3Transformer Residual StreamsModel Auditing

    Adelaide University, Adelaide, Australia

  4. Groundability, Not Scale Alone: When Weak Reviewers Can Audit Strong Coding Agents

    Oct 1, 2026Junyu Guo, Shangding Gu, Ming Jin +1Code QualityReviewer

    University of California, Berkeley · Virginia Tech

  5. TRACE: Privacy-Preserving Next-Best-View Selection over Distributed 3D Gaussian-Splat Maps

    Sep 30, 2026Amirhossein Mollaei Khass, Athanasios Cosse, Qiyu Sun +1Gaussian Splatting Simultaneous Localization And Mapping Systems3D Mapping

    Department of Mechanical Engineering and Mechanics, Lehigh University, Bethlehem, PA, 18015, USA

  6. TRACE: Trajectory Selection for Parallel Scaling of Search Agents

    Sep 30, 2026Qisheng Zhou, Zhen Xiong, Qiaoyu TanSearch AgentsTraces

    New York University Shanghai · New York University

  7. Plan-Conditioned Imitation for Robust Object Retrieval under Self-Occlusion in Dense Clutter

    Sep 30, 2026Kowndinya Boyalakuntla, Ajinkya Pawar, Abdeslam Boularias +1Behavior CloningOcclusion

    Rutgers University · Indian Institute of Technology Bombay, India

  8. CRAFT: Causal Responsibility and Failure Tracing in Medical Vision Language Models

    Sep 30, 2026Chunzheng Zhu, Jiaqi Zeng, Hongbo Zhao +3Medical Vision-Language ModelsVisual Evidence

    Hunan University · University of Hong Kong

  9. Hidden Reasoning Must Leak, but Need Not Be Readable: Fundamental Opportunities and Limits for Chain-of-Thought Monitoring

    Sep 29, 2026Mohammadali Mohammadkhani, Madhava Krishna, Yash Sarrof +1Chain-of-Thought ReasoningLarge Reasoning Models

    Saarland University, Saarland Informatics Campus · Zuse School ELIZA

  10. State Trace Rationale As Auxiliary Task in Reinforcement Learning

    Sep 29, 2026Muhammad U. Nasir, Alex Vogt, Steven D. James +1State-TrackingTraces

    University of the Witwatersrand Johannesburg, South Africa · New York University New York, USA

  11. DraftTrace: A Multi-View Analytics Environment for AI-Integrated Writing

    Sep 29, 2026Divyansh Chandarana, Sandipan De, Vivek GuptaAi-Assisted WritingWriting

    Arizona State University

  12. TRACE: Single-Pass Decoding-Trace Risk Localization for Generation Calibration

    Sep 28, 2026Yuebin Xu, Xuemei Peng, Junlan Chen +2Large Language Model UncertaintyConformal Risk Control

    The Hong Kong University of Science and Technology (Guangzhou)

  13. Accelerator Choice Is Not Enough: AlphaFold2 Inference on Cloud TPUs

    Sep 28, 2026Lorenzo Pazienza, Ihab El BaniShardTraces

    LUISS Guido Carli University Rome, Italy · Stanford University · Al Akhawayn University Ifrane, Morocco

  14. ControlTrace: Recovering Control Fields for Hidden-Content Recognition

    Sep 28, 2026Zijian Liu, Yaoguang Chen, Liwei Liu +4Field EvaluationTraces

    Shanghai Jiao Tong University · Ant Group

  15. Who Gets a Token, and What Does It Carry? Unequal Name Support and Concept Access in Large Language Models

    Sep 28, 2026Mir Tafseer Nayeem, Davood RafieiLarge Language Model BiasGender

    Department of Computing Science University of Alberta

  16. The Price of Peeking: Anytime-Valid Leakage Detection on ML-KEM EM Traces

    Sep 27, 2026Georgios Feretzakis, Alexandros PapaspyridisData LeakageWitnesses

  17. TRACE: Governing Memory Validity in Evolving Multi-Agent Systems

    Sep 27, 2026Wenjun Xiong, Shengtao Zhang, Shangding Gu +5TracesSingle-Agent Baselines

    Shanghai Jiao Tong University · MemTensor(Shanghai) Technology Co., Ltd. · UC Berkeley +1

  18. Traceprop: Training Data Attribution in a Single Pass

    Sep 26, 2026Amit NautiyalTraces

    Independent Researcher

  19. Analyzing and Mitigating Cost-Inefficient Behaviors in Coding Agents

    Sep 25, 2026Yiran Hu, Nan Jiang, Shanchao Liang +3Coding AgentsExacerbate Systemic Inefficiencies

    Purdue University

  20. LLM Agents Can Easily Tamper With Their Own Traces

    Sep 24, 2026Jeremy Qin, David Schmotz, Derck Prinzhorn +3TracesLarge Language Model Agents

    ELLIS Institute Tübingen · Max Planck Institute for Intelligent Systems · Tübingen AI Center +3

  21. TRACE: Interactive Bi-Directional Tracing of Monochrome Cables Amid Clutter

    Sep 24, 2026Nidhya Shivakumar, Ethan Ransing, Josh Zhang +6WiringTraces

    AUTOLab at the University of California, Berkeley

  22. TraceGuard: Adaptive Multimodal Poison Filtering through Cross-Feature Rank Agreement

    Sep 24, 2026Haoyang Li, Yaxin Xiao, Linyan Dai +5Text CorporaTraces

    The Hong Kong Polytechnic University · Commonwealth Scientific and Industrial Research Organisation (CSIRO)

  23. TraceVIC: Causal Reasoning over Code Evolution for Identifying Vulnerability-Inducing Commits

    Sep 22, 2026Fnu Tanish, Samiha Shimmi, Samikshya Chapagain +3Vulnerable CodeCommits

    Northern Illinois University · MIT Lincoln Laboratory

  24. When Are Aggregate Agent Traces Diagnosable? Traffic-Governed Interpretation and Calibrated Abstention

    Sep 22, 2026Peiying Zhu, Sidi ChangTracesFault Diagnosis

    Blossom AI San Francisco, CA, USA

  25. Canonical Procedural Actions: An Auditable Annotation Protocol for Tool-Use Agent Traces

    Sep 21, 2026Songqi Li, Dongqing Li, Zheqiao ChengTracesTool Invocation

    Cambridge Language Sciences, Raised Faculty Building, Sidgwick Avenue, Cambridge CB3 9DA, United Kingdom · Department of Statistics, University of Oxford, 24–29 St Giles’, Oxford OX1 3LB, United Kingdom · Zhejiang University, China

  26. ETH-TraceBench: A Large-Scale Event-Stream Benchmark for Ethereum DeFi under Temporal, Protocol, and Contract Shift

    Sep 20, 2026Kemal Kirtac, Carsten MapleDecentralized FinanceFinance Benchmarks

    Department of Computer Science, University College London 66–72 Gower Street, London WC1E 6EA, United Kingdom · Department of Computer Science, University of Warwick Coventry CV4 7AL, United Kingdom · WMG, University of Warwick Coventry CV4 7AL, United Kingdom

  27. TRACE: Tractable Routing Autoencoder for Clinical ECG

    Sep 20, 2026Shunbo Jia, Runze Ma, Haonan Lyu +3Electrocardiogram Foundation ModelsTraces

    Department of Bioelectronics, Faculty of Biomedical Engineering, Shenzhen University of Advanced Technology, Shenzhen, 518107, China · Faculty of Information Technology, Monash University, Clayton, Victoria, 3800, Australia · Faculty of Science, University of Queensland, Brisbane, 4072, Australia +1

  28. Fingerprinting Multimodal Large Language Models

    Sep 17, 2026Chao Huang, Meng Tong, Kejiang ChenMultimodal Large Language ModelsFingerprint

    University of Science and Technology of China Anhui Province Key Laboratory of Digital Security Hefei, Anhui, China

  29. TRACE: Accountable Agentic Retrieval for Source Discovery in Digital Archives

    Sep 17, 2026Donghan Bian, Marie Puren, Florian CafieroTracesArchive

    ENC, LRE · École nationale des chartes – PSL Centre Jean-Mabillon Paris, France · EPITA EPITA Research Laboratory Le Kremlin-Bicêtre, France +2

  30. Accurate Trace Estimation with Fewer Random Bits via Recursive TensorSketch

    Sep 16, 2026Mohammad Azhar Khan, Rameshwar Pratap, Amit SharmaMatrix MultiplicationRandom

    Indian Institute of Technology Hyderabad, Kandi, Sangareddy, 502284, Telangana, India.

  31. Beyond Accuracy: How Procedural Traces Shift the Decision Criterion of LLM Overseers

    Sep 16, 2026Zihan Chen, Di Zhu, Lei Zheng +1Model AuditingLarge Language Models Fail

    Stevens Institute of Technology Hoboken, NJ, USA · University of Massachusetts Boston Boston, MA, USA · Stony Brook University Stony Brook, NY, USA

  32. Touch2Trace: Tactile-Driven Imitation Learning for Dexterous Cable Tracing

    Sep 14, 2026Matteo Grimaldi, David Klee, Ziling Chen +5Contact-Rich Dexterous ManipulationTactile

    Dexterous AI Group, Analog Devices, Inc.

  33. TRACE: Two-Stage Detector-Response Estimation With Angular Cosine Expansion for Ring Artifact Correction in Photon-Counting CT

    Sep 14, 2026Jigang Duan, Heran Wang, Ligen Shi +3Cone-Beam Computed TomographyCompression Artifacts

    School of Mathematical Sciences, Capital Normal University, Beijing 100048, China · College of Computer Science (College of Software), Inner Mongolia University, Hohhot 010021, China · Research Center for Spatiotemporal Intelligence, Inner Mongolia University, Hohhot 010021, China

  34. What a gated sensing pipeline never looks at: bandwidth reduction and the misses behind it

    Sep 14, 2026Raghu Venkat, Tricha AnjaliDetection PerformanceObject Detection

    Numberz.ai Inc., Alpharetta, GA

  35. Feature Recovery for Object Understanding After Irreversible Fire Damage

    Sep 14, 2026Aditi Tiwari, Sofia Stoica, Savya Khosla +2Object DetectionFine-Grained Perception

    University of Illinois Urbana-Champaign Urbana, IL 61801

  36. Write on Paper and Get the Online Digital Trace:\newline A New Era for Handwriting

    Sep 14, 2026Florent Imbert, Yann Soullard, Eric Anquetil +5HandwritingTraces

    IRISA, Universit´e de Rennes, INSA Rennes, France · LTU, Machine Learning Group, Lule˚a University of Technology, Sweden · IRISA, Universit´e Rennes 2, France +2

  37. Tracing and Coordinating Cross-Layer Influence for Multimodal Model Merging

    Sep 14, 2026Pengyang Zhou, Xiaobin Tu, Zhengxi Liu +7Continual Model MergingMulti-Modal Data

    Alibaba Cloud

  38. MemRiskBench: Trace-Aware Risk-Preserving Evaluation for Long-Horizon LLM Agents

    Sep 14, 2026Jianhua Jiang, Dongbo Yuan, Weihua LiRiskTraces

    School of Artificial Intelligence and Computer Science, Jilin University of Finance and Economics, 130117 Changchun, China · Jilin Province Key Laboratory of Fintech, Jilin University of Finance and Economics, 130117 Changchun, China · School of Engineering, Computer and Mathematical Sciences, Auckland University of Technology, Auckland, New Zealand

  39. Tracing the Origins: Legacy Codec Identification in Neural Audio Transcoding

    Sep 14, 2026Wonje Heo, Shinee Youn, Yooshin Kim +2Neural Audio CodecsNeural Audio

    Department of Electrical Engineering and Computer Science (EECS), DGIST, Republic of Korea · School of Undergraduate Studies, DGIST, Republic of Korea

  40. Externalizing Requirement-to-Repair Artifacts as Observable Traces for LLM-Based Program Repair

    Sep 14, 2026Zewen Tao, Shin-nosuke IshikawaAutomated Program RepairRepair

    Rikkyo University

  41. Root-Cause Attribution Is a Search Problem: Continual Search for Long-Horizon Agent Failures

    Sep 11, 2026Harsh Raj, David Lee, Anas Mahmoud +7Root Cause AnalysisLong-Horizon Agents

    Scale AI · Scale AI Research

  42. SkillAtlas: An Attack Trace Library for Agent Skills

    Sep 11, 2026Yuxin Tian, Zenghao Duan, Liang Pang +2TracesAtlas

    State Key Laboratory of AI Safety, Institute of Computing Technology, CAS · University of Chinese Academy of Sciences

  43. OpenDiscoveryTrace: Process Traces for Evaluating AI Scientist Workflows

    Sep 10, 2026Aayam Bansal, Keertan BalajiArtificial Intelligence ScientistsTraces

  44. TRACE: Training Reasoning Agents for Causal Exploration with Synthesized Rewards

    Sep 9, 2026Rui Sun, Zhan Shi, Bing HeReinforcement Learning With Verifiable RewardReasoning Traces

    Independent Researchers

  45. TRACE: Trajectory-robust Admission with Evidence Ordering for Efficient GUI Agents

    Sep 9, 2026Yuhao Wang, Mu Qiao, Xindong Zhang +3Visual Token PruningTraces

    Dalian University of Technology · OPPO Research Institute · The Hong Kong Polytechnic University

  46. HyperTrace: Hypothesis-Based Preference Tracing for Online LLM Personalization

    Sep 9, 2026Jianzhi Shen, Keyu Mao, Minghao Shao +7Large Language Model PersonalizationPersonalization

    Johns Hopkins University · Institute of Science Tokyo · NYU Tandon +1

  47. ZK-Trace: Certified Collusion Tracing with Zero-Knowledge Credentials for Federated GNSS Interference Monitoring

    Sep 8, 2026Redwanul Karim, Nisha L. Raichur, Lucas Heublein +3Global Navigation Satellite SystemZero-Knowledge Proofs

    Fraunhofer Institute for Integrated Circuits IIS, 90411 Nürnberg, Germany

  48. The Oversight Gap: What LLM Safety Monitors Miss, and Why It Is Not Capability

    Sep 7, 2026Xin XuScalable OversightLarge Language Model Safety

    Carnegie Mellon University

  49. Parsing the Stream: A Live Trace Model for Long-Horizon Agents and Their Observers

    Sep 1, 2026Egor Pakhomov, Erik NijkampTracesLong-Horizon Agents

    Salesforce AI Research

  50. Replicating TRACE: A Practitioner's Guide to Its Threshold and Particle Budget

    Sep 1, 2026Alex Chadyuk, Alicia Zhang, Roy KucukatesCausal GraphTraces

    LotusFlare Inc.

  51. Perceptible or Not? Diagnosing Passive Fingerprints for Speech Deepfake Attribution

    Sep 1, 2026Yupei Li, Qiyang Sun, Emmanouil Benetos +2Audio Deepfake DetectionFingerprint

    1Imperial College London · 4Technical University of Munich · 2Queen Mary University of London +1

  52. Are We There Yet? Assessing Computer-Use Agents for Blind Users' Accessible Interaction with Desktop Applications

    Sep 1, 2026Satwik Ram Kodandaram, Monalika Padma Reddy, Xiaojun Bi +3Computer-Use AgentsTraces

    Stony Brook University · Old Dominion University

  53. The Answer Is Not the Argument

    Aug 31, 2026Will Yeadon, Sergio Juárez, Paul Mackay +5AnswerReasoning Traces

    Department of Physics, Durham University, Durham DH1 3LE, UK · Escuela de Ingenier´ıa de Telecomunicaci´on, Department of Signal Theory and Communications, University of Vigo, Vigo E-36310, Spain · Independent Researcher

  54. Will the User Ever Know? Covert Indirect Prompt Injection Attacks on Tool-Using LLM Agents

    Aug 31, 2026Yunseok Lee, Yunji Kim, Woojin LeeIndirect Prompt InjectionAttack-Success Rate

    Dongguk University-Seoul

  55. Tracing Generated Samples to Training-Data Clusters in Flow-Matching Models

    Aug 30, 2026Rania Briq, Ohad Fried, Michael Kamp +1Generative ModelsVelocity Field

    Forschungszentrum Jülich · Technical University Dortmund · Reichman University +4

  56. Perceive to Hypothesize, Verify to Ground: An Agentic Reasoning Framework for Open-World Geo-Localization

    Aug 30, 2026Yutian Jiang, Ruijie Li, Sisuo Lyu +4Cross-View Geo-LocalizationGrounding

    The Hong Kong University of Science and Technology (Guangzhou) · The Hong Kong University of Science and Technology

  57. TraceML: What Auto-Research Agents Miss in Long-Horizon ML Development

    Aug 26, 2026Jiarui Yan, Weiwei Sun, Sijie Li +2Mle-Bench LiteTraces

    Carnegie Mellon University

  58. TRACE: Trajectory Aware Reasoning for Multi-Turn Adversarial Conversation Evaluation

    Aug 16, 2026Md Messal Monem Miah, Adrita Anika, Zhiyuan Yu +1Jailbreak AttacksTrajectory-Aware Hidden-State Analyses

    Texas A&M University · Amazon

  59. TRACES: A Benchmark for Epistemic Reliability in Scientific Reasoning by LLMs

    Aug 11, 2026Valentin Rodionov, Shamil AssylbekovLarge Language Model ReliabilityScientific Discovery

    Intellicat Cleveland, OH 44106

  60. TRACE-GS: On-Policy Trajectory Distillation with Privileged Geometric Conditioning for Sparse-View 3DGS Restoration

    Aug 10, 2026Linlian Jiang, Yuchen Xi, Sadman Rakib Pinon +3Sparse-ViewTraces

    1Concordia University · 2Mila – Quebec AI Institute · 3Shanghai Jiao Tong University