| 1 | Same Outputs, Different Scores: Auditing the Unchecked Graders of Multimodal LLM Benchmarks | Ahmad Jarjis Hasan, Jonathan Lwowski | cs.AI | 2026-11-02 |
| 2 | What Structurally Breaks an Agent? Auditing Difficulty in Stateful Tool-Use Workflows | Shereen Anand, Ju Wang, Yali Du | cs.LG | 2026-11-02 |
| 3 | Rethinking Neural Decompilation: Candidate Selection as the Hidden Bottleneck | Felix Mächtle, Gautham Sriram, Manjil Neupane +2 | cs.CR | 2026-11-02 |
| #4 | The Customer Never Sees the Goal: Measuring and Detecting Vulnerability-Targeted Manipulation in LLM Assistants | Bohan Jiang, Dawei Li, Yasin Silva +1 | cs.CR | 2026-11-02 |
| #5 | Auditing Representation-Space Fraud Detection: A Bayesian IRL Framework for Calibrated Uncertainty and Its Limits | Shivam Swarup, Divya Prakash Shrivastava, Rakesh Thakur | cs.AI | 2026-11-02 |
| #6 | Probing Local Conditional Fit for Diffusion Model Membership Inference | ByungHee Cha, Naoki Murata, Yuhta Takida +2 | cs.AI | 2026-11-02 |
| #7 | Opening the Black Box of Neural Auction Mechanisms | Li Kong, Zilong Liu, Haoyang Zhou +2 | cs.AI | 2026-11-01 |
| #8 | Launder-Bench: Can Repository-Level Agentic Code Laundering Be Detected? | Yuntong Hu, Hongji Pu, Zimo Li +5 | cs.SE | 2026-11-01 |
| #9 | A Compute Center Anyone Can Join: A Peer-to-Peer System for AI Inference | Yimo Lin, Zhen Zhang | cs.AI | 2026-11-01 |
| #10 | Silent Reward and Environment Defects in EV Charging Simulation Benchmarks: A Diagnostic Checklist | Nour-Eddine Moumni, Rachid Alaoui, Driss Kiouach | cs.LG | 2026-11-01 |
| #11 | Halal-NeSyNet: Clause-Scoped Neuro-Symbolic Cross-Attention for Automated Food Ingredient Auditing and Risk-Aware Halal Logistics Triage | Mochamad Rizal Fauzan, Naila Nursyifa, Irgi Surya | cs.CL | 2026-11-01 |
| #12 | From Tool State to Scientific Action: Auditing Decision Provenance in Biomedical Research Agents | Xingyu Yi, Xinya Zhang, Yunshen Zhou +1 | cs.AI | 2026-11-01 |
| #13 | Abstention Spends Its Budget on Local Label Variance More Than on Novelty: Auditing Conformal Calibration and Selective Prediction under Molecular Scaffold Shift | Arnav Srivastava, Krishna Kassetty | cs.LG | 2026-11-01 |
| #14 | CONFIRM: Governing Scientific Reporting for Trustworthy Agentic Neuroimaging | Yuxiang Wei, Lijing Zhu, Qizhen Lan +2 | cs.AI | 2026-11-01 |
| #15 | Context-Shielded Backdoor Attack against Large Vision-Language Models | Zhifang Zhang, Qiang Huang, Chenpeng Wang +6 | cs.CV | 2026-10-31 |
| #16 | World Models Need Not Be Right to Rank Policies Right: Relative Bounds and Audit Limits | Ahanaf Hasan Ariq, Hasaan Ahmad | cs.LG | 2026-10-31 |
| #17 | What Does a Safety Label Measure? Auditing Situational-Safety Benchmarks for Multimodal LLMs | Wayner Barrios, Kenneth Barrios | cs.CV | 2026-10-31 |
| #18 | CogRSI: Evolving and Auditing Cognitive Reasoning Strategies | Yandan zheng, Haoran Luo, Xinliang Zhou +1 | cs.CL | 2026-10-31 |
| #19 | From Apparent Search Gains to Selection Failures: Auditing Test-Time Inference in Structured Workflow Planning | Zhitong Chen, Weifeng Zhang, Kai Yin +3 | cs.CL | 2026-10-31 |
| #20 | WAR-CRAFT: Refining Web API Recommendations through Requirement Auditing | Zishuo Xu, Dezhong Yao, Zhiqiang Xu | cs.AI | 2026-10-31 |
| #21 | AStockArena: Beyond Returns, Can We Entrust Real Capital to the Decisions of Financial Agents? | Zeyu Liu, Sing Kwong Lai, Xuanzhi Feng +4 | cs.CL | 2026-10-31 |
| #22 | Do Social Influence Pressures Move LLM Agents? Evidence from Delegated Audit Judgment | Richard Zhe Wang | cs.CY | 2026-10-31 |
| #23 | Swap, Replicate, Read the Mass: A Protocol for Auditing Demographic Bias in System One Decision Models | Alejandro Mozo Quesada, Sergio Gálvez Rojas, Francisco López Valverde | cs.AI | 2026-10-31 |
| #24 | A Straight Line Is Not a Camera Pose: Auditing Short-Clip Pose Benchmarks | Xinyi Shi | cs.CV | 2026-10-31 |
| #25 | Same Question, Different Answers: Auditing Persona-Dependent Variation in Six LLMs on Smoking-Cessation Advice | Artin Yousefi, Aizierjiang Aiersilan, Lorien C Abroms +1 | cs.AI | 2026-10-30 |
| #26 | AI evaluators favor job applications written by certain AI models, independent of candidate quality | Nicolò Pagan, Michael Andreas Ebling, Stefania Ionescu +1 | cs.CY | 2026-10-30 |
| #27 | ReuScope: Auditing Data Reuse and Evaluation Sensitivity in Capsule Vision 2024 | Eunseob Choi, Kyeonghun Kim, Hyuk-Jae Lee +1 | cs.AI | 2026-10-30 |
| #28 | Different Models, Shared Failures: Auditing Frozen-Encoder Pools for Medical Segmentation | Eunseob Choi, Kyeonghun Kim, Hyuk-Jae Lee +1 | cs.CV | 2026-10-30 |
| #29 | Measuring What Matters: A Causal Reliance Score for Histopathology Image Segmentation | Samuel Thomas, Daniel Tweneboah Anyimadu, Ahmed Karam Eldaly +2 | cs.CV | 2026-10-30 |
| #30 | When Safety Checks Become Privacy Risks: A Privacy-Preserving Paradigm for LLM Agent Safety Auditing | Yixiang Luo, Ziheng Ma, Ke Chang +2 | cs.CR | 2026-10-30 |
| #31 | From the Zoo to the BULLPEN: Sample-Efficient LLM Profiling via Multi-Channel Model Embeddings | Russell Ro, Qiming Cui, Reza Abbasi-Asl | cs.AI | 2026-10-30 |
| #32 | Do Transaction Prices Reflect Visual Preference? A Diagnostic Study with Multimodal Language Models | Fengxian Ji, Jingpu Yang, Fan Zhang +6 | cs.AI | 2026-10-30 |
| #33 | StrictPRMBench: A Replayable Evaluation Benchmark for Auditing Fixed-Score PRM Aggregation | Pengfei Zheng | cs.LG | 2026-10-30 |
| #34 | Difficulty Calibration Across Time for Membership Inference in Diffusion Models | Michael Joseph, Yedid Hoshen | cs.CV | 2026-10-29 |
| #35 | Agentic LLM reasoning in pediatric diabetes outcome prediction from multimodal medical records | Daniel Palacios, Guantong Qi, Anna Kadi +8 | q-bio.QM | 2026-10-29 |
| #36 | EnvOS: Auditing Computer-Use Agents When the World Moves On : Phenomenon-Based Task Construction, Certification, and Evidence-Based Evaluation | Ankush Kadu, Athira Gopal, Niharika Singh +2 | cs.AI | 2026-10-29 |
| #37 | MemSteer: Turning User Histories into Supervision for Agent Memory Optimization | Jie Huang, Cuiling Lan, Qize Yu +2 | cs.AI | 2026-10-29 |
| #38 | Loss is Not Behavior: A Unified Output-Space Analysis of Gradient-Based Machine Unlearning | Xingjian Zhao, Mohammad Mohammadi Amiri, Malik Magdon-Ismail | cs.LG | 2026-10-28 |
| #39 | Alpha-TCM: A Nine-Layer Framework for TCM-Guided Multimodal Inference and Structured-Prior Auditing | Yucheng Liu, Everett X. Wang | cs.LG | 2026-10-28 |
| #40 | Beyond fabrication: Misattributed numbers in papers written by AI research agents | Mosab Alfaqeeh, Omar Hourani, Muath Hourani +1 | cs.AI | 2026-10-28 |
| #41 | Value Probes: Learned Value Functions for Beam-Search Red Teaming | Jonathan F. Jao, Andrew Kyle Lampinen | cs.AI | 2026-10-28 |
| #42 | Masked Erosion: How Acceptance Gates Lose Redundant Safeguards in Self-Improving Agents | Hau-Sing So, Daixian Liu, Weicai Long | cs.AI | 2026-10-28 |
| #43 | Visually Irrelevant Hallucinations in Medical Vision-Language Models | Ke Zou, Nan Zhou, Tao Yang +9 | cs.CV | 2026-10-28 |
| #44 | The Indian Financial Automated Advice Bias (IFAAB) Dataset : Auditing Socioeconomic and Demographic Disparities in LLM-Generated Financial Advice in India | Kriti Mahajan | cs.CY | 2026-10-28 |
| #45 | From Error Prediction to Causal Influence: Auditing SAE Features in Multiple-Choice QA | Aria Nourbakhsh, Adelaide Danilov, Oleksandr Marchenko Breneur +1 | cs.CL | 2026-10-27 |
| #46 | Statistical Detection of Positional Bias in LLM-Based Recommender Systems: Methodologies and Empirical Evidence | Carlos Peláez-González, Francisco Herrera, Andrés Herrera-Poyatos | cs.IR | 2026-10-27 |
| #47 | Blindfold: Keeping the Audit Coin Secret from LLM Agents | Wei Zhu, Meiyun Zuo, Huiping Sun | cs.CR | 2026-10-27 |
| #48 | Do AI Scientists Know What's New? | Miri Liu, Xiayu Zhao, Encheng Xie +1 | cs.CL | 2026-10-27 |
| #49 | Identity or Evidence? Auditing Evidence Dependence in Agentic Life-Science Benchmarks | Danai Brilli, Maria Georgila | cs.CV | 2026-10-27 |
| #50 | Base Models Can Detect Hidden Intentions that Prompted Classifiers Miss | Oz Amram | cs.LG | 2026-10-26 |