Second Workshop on Agents in the Wild: Safety, Security, and Beyond

Accepted papers (216)

Fetched from OpenReview (v2) on 2026-06-10.

1. A Multi-Model Self-Evolving Framework for Zero-Data Document Understanding via Axiomatic Synthetic Refinement

   Yuwen Tao, Fuxiao Liu

2. A Prompt-Masked Pilot for History-Dependent Safety Degradation in Multi-Turn Conversational Agents

   Bright Liu, Lia Zheng, Natalia Siwek, Karina Chung

3. A Systematic Investigation of RL-Jailbreaking in LLMs

   Montaser Mohammedalamen, Kevin Roice, Reginald McLean, Alyssa Lefaivre Škopac

4. ABRA: Agent Benchmark for Radiology Applications

   Bulat Maksudov, Vladislav Kurenkov, Kathleen M Curran, Alessandra Mileo

5. Activation Steering for Tool-Poisoning Defense in Language-Model Agents

   Artem Zhuravel, Hubert M. Pysklo

6. Adaptive Adversaries: A Multi-Turn, Multi-LLM Benchmark for LLM Agent Security

   Devina Jain, David Hartmann, Chuan Li

7. AF-ARENA: A Multi-Dimensional Evaluation Suite for Alignment Faking

   Chijioke Ugwuanyi, Terry Jingchen Zhang, Zhijing Jin

8. Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks

   Yoonsang Lee, Howard Yen, Xi Ye, Danqi Chen

9. Agentic Misalignment Deterrence: Incorporating Probability and Stakeholders to Decision-Making

   Karthik Reddy Konuganti, Ryan Co

10. Agentic Reinforcement Learning for Search Misaligns Instruction-Tuning

    Yushi Yang, Shreyansh Padarha, Sarah Ball, Andrew Lee, Adam Mahdi

11. AgentSociety: Incentivizing Agentic Social Intelligence

    Aditya Vema Reddy Kesari, Krishna Reddy Kesari

12. AI Agent Safety is a Reinforcement Learning Problem

    Reginald McLean, Tabitha Edith Lee, Montaser Mohammedalamen, Kevin Roice, Glen Berseth, Patrick M. Pilarski, Marlos C. Machado, Alyssa Lefaivre Škopac, Benjamin Rosman

13. AI Safeguards as Affordance Modulation: Embedded Population Assumptions in Agentic Systems

    Sumaya Nur Adan

14. Aligning Language Models with Selective Prediction

    Gaoxiang Luo, Yifan Wu, Sinian Zhang, Aryan Deshwal, Ju Sun

15. Approve the Effect, Not the Tool Call: Preventing Stale Consent in Tool-Using Agents

    Qi Zhang

16. Architecture Matters for Multi-Agent Security

    Ben Hagag, William L. Anderson, Christian Schroeder de Witt, Sarah Scheffler

17. ARLArena: A Unified Framework for Stable Agentic Reinforcement Learning

    Xiaoxuan Wang, Han Zhang, Haixin Wang, Yidan Shi, Ruoyan Li, Kaiqiao Han, Chenyi Tong, Haoran Deng, Alexander K Taylor, Renliang Sun, Yanqiao Zhu, Jason Cong, Yizhou Sun, Wei Wang

18. ASPI: Seeking Ambiguity Clarification Amplifies Prompt Injection Vulnerability in LLM Agents

    Udari Madhushani Sehwag, Zhengyang Shan, Heming Liu, Dileepa Lakshan, Joseph Brandifino, Max Fenkell

19. ATLAS: Adaptive Topology-Level Attack Synthesis for Probing Multi-Agent Systems

    Raja Sekhar Rao Dheekonda, Vincent Abruzzo

20. Attack Selection in Agentic AI Control Evaluations Meaningfully Decreases Safety

    Tyler Crosse, Catherine Ge-Wang, Benjamin Hadad, Joachim Schaeffer, Ram Potham, Tyler Tracy

21. Attractor States Emerge in Multi-Turn LLM Conversations

    Ting-Wen Ko, Jonas Geiping

22. Autoformalization of Agent Instructions into Policy-as-Code

    Adam Mondl, Matthew Maisel, John H. Brock

23. AutoHoney: Automating, Deploying, and Evaluating Scheming Honeypots Across Production Codebases

    Martin Ciesielski-Listwan, Alyssia Jovellanos, Victoria Krakovna

24. Automata from Agent Traces: Failure and Next-Step Prediction

    Seonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed, Zekun Wu, Kleyton Da Costa, Ilham Wicaksono, Adriano Koshiyama

25. Automated interpretability and feature discovery in language models with agents

    Arnau Marin-Llobet, Javier Ferrando

26. BARRED: Synthetic Training of Custom Policy Guardrails via Asymmetric Debate

    Arnon Mazza, Elad Levi

27. BarrierSteer: LLM Safety via Learning Barrier Steering

    Thanh Q. Tran, Arun Verma, Kiwan Wong, Bryan Kian Hsiang Low, Daniela Rus, Wei Xiao

28. Behavioral Code: Legible, Auditable Loops for Autonomous Agents

    Abutalib Namazov, Tae Wook Kim, Eagon Meng, Daniel Jackson

29. Behavioral Determinants of Deployed AI Agents in Social Networks: A Multi-Factor Study of Personality, Model, and Guardrail Specification

    Sarah Wilson, Diem Linh Dang, Usman Ali Moazzam, Shan Ye, Gail Kaiser

30. Beyond Single-Model Injection: A Threat Model and Defense Architecture for Prompt Injection in Multi-Agent Systems

    Rudrendu Kumar Paul, Sourav Nandy

31. Bias and Discrimination in the Agentic Web and How Project NANDA Can Support Mitigation

    Sundaraparipurnan Narayanan

32. BiasTrojan: LLM Judgers Are Easily Distorted by Few Hundreds of Contrastive Biased Training Data

    Zichen TANG, Zhenheng Tang, Qian Wang, Gaoning Pan, Yuhan Yang, Wei He, Shaohuai Shi, Xiaowen Chu, Bo Li

33. BioAgent Bench: An AI Agent Evaluation Suite for Bioinformatics

    Dionizije Fa, Marko Culjak, Bruno Pandza, Mateo Čupić

34. Boundary Point Jailbreaking of Black-Box LLMs

    Xander Davies, Giorgi Giglemiani, Edmund Lau, Eric Winsor, Geoffrey Irving, Yarin Gal

35. Bridging Safety and Performance in Autonomous Systems using Offline Reinforcement Learning

    Mumuksh Tayal, Manan Tayal, Ravi Prakash

36. CAD-bench: Benchmarking Language Models on Functional CAD Generation

    Dhruv Saini

37. Calibrated Deferral Routing for Cost-Efficient Guardrails

    Giandomenico Cornacchia, Inkit Padhi, Manish Nagireddy, Subhajit Chaudhury, Pierre Dognin, Tejaswini Pedapati, Ambrish Rawat, Mark Purcell, Kush R. Varshney, Prasanna Sattigeri

38. CaMeLs Can Use Computers Too: System-level Security for Computer Use Agents

    Hanna Foerster, Tom Blanchard, Kristina Nikolić, Ilia Shumailov, Cheng Zhang, Robert D. Mullins, Nicolas Papernot, Florian Tramèr, Yiren Zhao

39. CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models

    Swapnil Parekh

40. Catching Infrastructure Sabotage When Coding Agents Are Insider Threats

    Preeti Ravindra, Rahul Tiwari

41. Caught in the Act(ivation): Stopping Credential Exfiltration Before It Starts

    Kargi Chauhan, Pratibha Revankar

42. Chain of Risk: Safety Failures in Large Reasoning Models and Mitigation via Adaptive Multi-Principle Steering

    Xiaomin Li, Jianheng Hou, Zheyuan Deng, Zhiwei Zhang, Taoran Li, binghang lu, Bing Hu, Yunhan Zhao, Yuexing Hao

43. Chain-of-Sanitized-Thoughts: Reducing PII Leakage in Chain-of-Thought Reasoning

    Arghyadeep Das, Sai Sreenivas Chintha, Sharvi Endait, Rishiraj Girmal, Kinjal Pandey

44. ChainCaps: Composition-Safe Tool-Using Agents via Monotonic Capability Attenuation

    Xiaochong Jiang, Shiqi Yang, Ziwei Li, Lifei Liu, Haoran Yu, Yichen Liu

45. Chasing the Public Score: User Pressure and Evaluation Exploitation in Coding Agent Workflows

    Hardy Chen, Nancy Lau, Haoqin Tu, Shuo Yan, Xiangyan Liu, Zijun Wang, Juncheng Wu, Michael Qizhe Shieh, Cihang Xie, Yuyin Zhou

46. Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs

    Alexander Panfilov, Peter Romov, Igor Shilov, Yves-Alexandre de Montjoye, Jonas Geiping, Maksym Andriushchenko

47. ClinSeekAgent: Automating Multi-modal Evidence Seeking for Agentic Clinical Reasoning

    Juncheng Wu, Letian Zhang, Yuhan Wang, Haoqin Tu, Hardy Chen, Zijun Wang, Cihang Xie, Yuyin Zhou

48. Coding Agents Don't Know When to Act

    Thibaud Gloaguen, Niels Mündler, Mark Niklas Mueller, Veselin Raychev, Martin Vechev

49. Communication Boundary Control for Safer Multi-Agent Language Agents

    Max Ruiz Luyten, Mihaela van der Schaar

50. Component and Dimension Sparsity in Transformer Refusal Mechanisms

    Vincent Siu, Glenn Grant-Richards, Vlad Pavlovich, Yizhou Sun, Dawn Song, Chenguang Wang

51. Compound AI System Reliability: A Failure Taxonomy and Resilience Pattern Catalog from 150 Production Incidents

    Rudrendu Kumar Paul, Sourav Nandy

52. Consensus–Bayesian Anomaly Detection in Agentic Access Graphs

    Pratyush uppuluri, Shilpa Noushad, Sajan Kumar, Jayanth Poosarla

53. Containment Verification: AI Safety Guarantees Independent of Alignment

    Royce Moon, Lav R. Varshney

54. CONTRA: Red-Teaming Configurations of Personalizable Agents

    Jonathan Nöther, Adish Singla, Goran Radanovic

55. Contrastive Discovery: Open-Ended Scientific Discovery over Competing Explanations

    Ziang Liu, James J. Kim, Yijia Dai, Jennifer J. Sun

56. Controlling Tool Use with Heading-Specific Activation Steering

    Yuqi Chen, Vincent Siu, Yang Liu, Dawn Song, Chenguang Wang

57. Copy-on-Write Scoring: Application-Specific Agent Evaluations

    Joanna Roy, Sven Hoelzel

58. Correcting Noise-Mispecified Operator Selection in Wild Compound LLM Agents

    Jiayi Qiu

59. Coverage-Aware Test Generation for Conversational AI Agents

    Mridul Katta, Darin Glatt

60. CPPO: Contrastive Perception Policy Optimization for VLM Agents

    Ahmad Rezaei, Mohsen Gholami, Saeed Ranjbar Alvar, Kevin Cannons, Mohammad Asiful Hossain, Zhou Weimin, Yong Zhang, Mohammad Akbari

61. Cross-Agent Campaign Attribution: Linking Asynchronous Attacks Across LLM Agents

    SangJin Park, Myungsub Choi, Jineok Kim, Minseung Kang

62. CrossAnchor: Image-Anchored Text Optimization Exposes Blind Spots in Multi-line Defenses of Agentic Systems

    Anish Kiran Kulkarni, Ravikumar Balakrishnan, Prashanth Arun

63. CTFusion : A CTF-based Benchmark for LLM Agent Evaluation

    Dongjun Lee, Ga-eun Bae, Insu yun

64. Decomposing Smooth Agentic Inference Scaling

    Ole Kristian Jorgensen, Rivka Mitchell, Tom Rainforth, Cozmin Ududec

65. Digital Twin Builder: A Multi-Agent LLM System for Automated Industrial Digital Twin Development

    Maria Dziuba, Elizaveta Egorova, Nikolay Vasilev, Ilya Novitskiy, Vladislav Tuchin, Valeria Efimova

66. Directional Alignment Mitigates Reward Hacking in Reinforcement Learning for Language Models

    Wenlong Deng, Jiaji Huang, Kaan Ozkara, Yushu Li, Christos Thrampoulidis, Xiaoxiao Li, Youngsuk Park

67. Do AI Agents Write Less Maintainable Code Than Human Developers?

    Betty Li Hou, Shaswat P Patel, Arun Purohit, Kai Xu, Jane Pan, He He, Valerie Chen

68. Does the Optimal Hallucination Detector for Agentic Tool Calls Depend on Model Scale?

    Valentin NOËL, Kait Healy, Visakh Madathil, Bharathi Srinivasan

69. Double-Helix Co-Training for Computer-Use Generator and Verifier Models

    Jikun Kang, Yi Heng Lim, Alex James Chan

70. Dynamic Capability Scoping for Enterprise AI Agents: A Synthetic Dataset and Three-Source Permission Architecture

    Halil Burak Noyan

71. Emergent Social Intelligence Risks in Generative Multi-Agent Systems

    Yue Huang, Yu Jiang, Wenjie Wang, Haomin Zhuang, Xiaonan Luo, Yuchen Ma, Zhangchen Xu, Zichen Chen, Nuno Moniz, Zinan Lin, Pin-Yu Chen, Nitesh V. Chawla, Nouha Dziri, Huan Sun, Xiangliang Zhang

72. Ensemble Monitoring for AI Control: Diverse Signals Outweigh More Compute

    Yejun Yun, Samantha Tetef, Eugene Koran, Pablo Bernabeu-Perez, Benjamin Arnav

73. Evaluating Agentic Configuration Repair for Computer Networks

    Rufat Asadli, Benjamin Hoffman, Ioannis Protogeros, Laurent Vanbever

74. Evaluation Theater: How Structural Compliance Decouples from Cognitive Judgment in Deployed LLM Agents

    Ning Coeva

75. EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience

    Taofeng Xue, Chong Peng, Mianqiu Huang, Linsen Guo, Tiancheng Han, Haozhe Wang, Xiaocheng Zhang, Xin Yang, Dengchang Zhao, Jinrui Ding, Xiandi Ma, Yuchen Xie, Peng Pei, Xunliang Cai, Xipeng Qiu

76. Extracting Recurring Vulnerabilities from Black-Box LLM-Generated Software

    Tomer Kordonsky, Amit LeVi, Maayan Yamin, Noam Benzimra, Avi Mendelson

77. Failure-Aware Query Refinement for Reliable Open-Vocabulary Home-Robot Perception

    Daun Jeong, Sohyeon Kim, Jouwon Song, Kyeongbo Kong

78. FaultLoc: Evaluating Coding Agents For Fault Localization

    Jianhong Tu, Shubham Gaur, Rathik Murtinty, Zhun Wang, Tianneng Shi, Dawn Song, Chenguang Wang

79. From Business Metrics to Behavioral Personas Controllable User Simulation for Pre-Deployment Agent Testing

    Zhenyu Zhang, Yuan Ling, Dingyang Chen, Xinyang Shen

80. From Reward-Hack Activations to Agentic Risk States: Context-Calibrated Mechanistic Monitoring in LLM Agents

    Patrick Wilhelm, Odej Kao

81. From Segments to Scenes: Temporal Understanding for Agentic Autonomous Driving via Vision-Language Models

    Kevin Cannons, Saeed Ranjbar Alvar, Mohammad Asiful Hossain, Ahmad Rezaei, Mohsen Gholami, Alireza Heidari, Zhou Weimin, Yong Zhang, Mohammad Akbari

82. From Self-Preservation to Peer-Preservation: A Staged Framing of Preservation-Oriented Misalignment in Frontier Models

    Rundong Yang

83. From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents

    Pritam Dash, Tongyu Ge, Aditi Jain, Tanmay Shah, Zhiwei Shang

84. FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback

    Xueqing Wu, Zihan Xue, Da Yin, Shuyan Zhou, Kai-Wei Chang, Nanyun Peng, Yeming Wen

85. Full-Season Agent Evaluation in Soybean Farm Operations under Real-World Agricultural Process Dynamics

    Ao Qu, Panagiotis Michelakis, Yiannis Hadjiyianni, Feng Li, Jingchi Jiang, Dimitrios Stamoulis, Jie Liu

86. Game-Theoretic Multi-LLM Routing for Safer Agents in the Wild

    Jing Wang, Jie Shen, Dean Foster, Zohar Karnin

87. GameDevBench: Evaluating Agentic Capabilities Through Game Development

    Wayne Chi, Yixiong Fang, Arnav Yayavaram, Siddharth Yayavaram, Seth Karten, Qiuhong Anna Wei, Runkun Chen, Alexander Wang, Valerie Chen, Ameet Talwalkar, Chris Donahue

88. General Agent Evaluation

    Elron Bandel, Asaf Yehudai, Lilach Eden, Yehoshua Sagron, Yotam Perlitz, Elad Venezian, Natalia Razinkov, Natan Ergas, Shlomit Shachor Ifergan, Segev Shlomov, Michal Jacovi, Leshem Choshen, Liat Ein-Dor, Yoav Katz, Michal Shmueli-Scheuer

89. Goal-Drift Probes: Anticipating Multi-Turn LLM Agent Failure From Mid-Network Activations

    Oliver Yangluo Chen

90. Hidden in Memory: Sleeper Memory Poisoning in LLM Agents

    Sidharth Pulipaka, Stanislau Hlebik, Leonidas Raghav, Sahar Abdelnabi, Vyas Raina, Ivaxi Sheth, Mario Fritz

91. Hidden in Plain Sight: Benchmarking Agent Safety Against Decomposition Attacks with DecompBench

    Vikhyath Kothamasu, Virginia Smith, Chhavi Yadav

92. HiMA: Efficient Hybrid Model Serving for Agentic Systems

    Yuzhou Nie, Weifang Zhang, Zhen Xu, Songyang Peng, Yuheng Tang, Minzhou Pan, Bo Li, Dawn Song, Ce Zhang, Wenbo Guo

93. Honeyval: A Comprehensive Evaluation Framework for LLM-powered HTTP Honeypots

    Mark Vero, Fabian Kaczmarczyck, Ivan Petrov, Ilia Shumailov, Niels Heinen, Jamie Hayes, Tianqi Fan, Luca Invernizzi, Martin Vechev

94. House Rules: Institutional Design in Multi-Agent LLM Code Markets

    Tony O'Halloran, Allison Claire Zhuang, Michael Zhang, Thibault Soubeste, Alexandre Sallinen, Stefan Krsteski, Charlotte Meyer, Guillaume Allegre, Kailey Seiler

95. How can we assess human-agent interactions? Case studies in software agent design

    Valerie Chen, Rohit Malhotra, Xingyao Wang, Juan Michelini, Xuhui Zhou, Aditya Bharat Soni, Hoang H. Tran, Calvin Smith, Ameet Talwalkar, Graham Neubig

96. How Far Are VLMs from Privacy Awareness in the Physical World? An Empirical Study

    Junran Wang, Xinjie Shen, Zehao Jin, Pan Li

97. How Should Your Agent Talk to Mine? Measuring the Utility–Security Frontier of Cross-Boundary Agentic Delegation

    Xisen Wang, Adel Bibi, Kevin Qinghong Lin, Philip Torr, Jindong Gu

98. How Well Do Models Follow Their Constitutions?

    Arya Jakkli, Senthooran Rajamanoharan, Neel Nanda

99. HowLLMDecision Agents Fail in the Wild: AReproducible Failure-Cell Framework

    Anthony Cruz

100. InferenceBench: A Benchmark for Open-Ended LLM Inference Optimization by AI Agents

     Jehyeok Yeon, Ben Rank, Maksym Andriushchenko

101. Internal vs. External: Comparing Deliberation and Evolution for Multi-Agent Constitutional Design

     Hershraj Niranjani, Ujwal Kumar, Phan Xuan Tan

102. Internal-State Probes Read the Situation, Not the Action: Three Negative Results for Pre-Action Misalignment Monitoring

     Max Fomin, Elad David, Amit LeVi

103. iOSWorld: A Benchmark for Personally Intelligent Phone Agents

     Lawrence Keunho Jang, Mareks Woodside, Geronimo Carom, Andrew Keunwoo Jang, Jing Yu Koh, Ruslan Salakhutdinov

104. Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)

     Zichen TANG, Zirui Zhang, Qian Wang, Zhenheng Tang, Xiaowen Chu, Bo Li

105. It's a TRAP! Task-Redirecting Agent Persuasion Benchmark for Web Agents

     Karolina Korgul, Yushi Yang, Arkadiusz Drohomirecki, Piotr Blaszczyk, Will Howard, Lukas Aichberger, Chris Russell, Philip Torr, Adam Mahdi, Adel Bibi

106. Knowing When to \texttt{STOP}, \texttt{RECOVER}, and \texttt{SEARCH} \\ A Modular Framework for GUI Automation

     Qijun Han, Haoqin Tu, Zijun Wang, Haoyue Dai, Yiyang Zhou, Nancy Lau, Alvaro A. Cardenas, Yuhui Xu, Ran Xu, Caiming Xiong, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie

107. Latent Undertow: How Ordinary Typos Break Probes

     Elad David, Max Fomin, Amit LeVi

108. Lateral Data Exfiltration in MCP: How One Compromised Server Captures Cross-Domain Agent Data

     Akshat Sharda, Zhenyu Zhang

109. Laundering AI Authority with Adversarial Examples

     Jie Zhang, Pura Peetathawatchai, Florian Tramèr, Avital Shafran

110. Learning Stateful Predictive Knowledge From Experience

     Yan Song, Xidong Feng, Bo Liu, Xinyu Cui, Zichen Liu, Haotian Fu, Mengyue Yang, Cheng Deng, Jian Zhao, Jun Wang

111. Learning to Inject: Automated Prompt Injection via Reinforcement Learning

     Xin Chen, Jie Zhang, Florian Tramèr

112. Learning to Learn-at-Test-Time: Language Agents with Learnable Adaptation Policies

     Zhanzhi Lou, Hui Chen, Yibo Li, Qian Wang, Bryan Hooi

113. LegalHalluLens: Typed Hallucination Auditing and Calibrated Multi-Agent Debate for Trustworthy Legal AI

     Lalit Yadav, Akshaj Gurugubelli

114. Liability Frameworks for Agentic AI Systems

     MARCEL OSMOND

115. Life After Benchmark Saturation: A Case Study of CORE-Bench

     Nitya Nadgir, Sayash Kapoor, Kangheng Liu, Peter Kirgis, Matilda Orona, Stephan Rabanser, Tilman Bayer, Abhishek Shetty, Yue Ling, Derrick Chan-Sew, Rumi Nakagawa, Saiteja Utpala, Zachary S Siegel, Arvind Narayanan

116. Linguistic Firewall: Geometry as Defense in Multi-Agent Systems Routing

     Dvir Alsheich, Adar Peleg, Ben Hagag, Rom Himelstein, Amit LeVi, Avi Mendelson

117. LinuxArena: A Control Setting for AI Agents in Live Production Software Environments

     Tyler Tracy, Ram Potham, Nikolas Kuhn, Myles Heller, Anshul Khandelwal, Cody Rushing, Henri Lemoine, Miguel Brandão, Tomáš Turlík, Adam Hanson, Josh Hills, Amy Dieu-Am Ngo, Ram Rachum, Nik Mitchell, Falko Galperin, Oscar Sykes, Pip Arnott, Samuel Prieto Lima, Carlos Rafael Giudice, Matt Goldwater, Daniel J Popp, Drew de Wet, Ruben Castaing, Qi Guo, Douw Marx, Benjamin Shaffrey, Justin Shenk, Martin Milbradt, Hannah Meagher, Shaheen Ahmed-Chowdhury, Daniel O'Connell, Christopher William Canal, Buck Shlegeris, Aryan Bhatt

118. LLM-Guided Planning for Multi-hop Reasoning over Multimodal Nuclear Regulatory Documents

     mingyu jeon, Bokyeong Kim, Suwan Cho, Jae Young Suh, Yonggyun Yu

119. LLMs Struggle to Rank Products Robustly

     Kumail Alhamoud, Charikleia Moraitaki, Carlos Hinojosa, Jennifer Zhou, Yuexing Hao, Philip Torr, Adel Bibi, Marzyeh Ghassemi

120. Lost in the Maze: Overcoming Context Limitations in Long- Horizon Agentic Search

     Howard Yen, Yoonsang Lee, Ashwin Paranjape, Mengzhou Xia, Thejas Venkatesh, Jack Hessel, Danqi Chen, Yuhao Zhang

121. MacArena: Benchmarking Computer Use Agents on an Online macOS Environment

     Victor Muryn, Maksym Shamrai, Sofiia Mazepa, Yehor Khodysko

122. Making Open-Source Text LLM Watermarks Durable Against Merging

     Luisa Scharff, Thibaud Gloaguen, Robin Staab, Martin Vechev

123. Measuring Five-Nines Reliability: Sample-Efficient LLM Evaluation in Saturated Benchmarks

     Eungyeup Kim, Chenchen Gu, Vashisth Tiwari, J Zico Kolter

124. Mecha-nudges for Machines

     Giulio Frey, Kawin Ethayarajh

125. Mechanism Design Is Not Enough: Prosocial Agents for Cooperative AI

     Xuanqiang Angelo Huang, Charlie Tharas, Samuele Marro, Van Q. Truong, Bernhard Schölkopf, Emanuele La Malfa, Zhijing Jin

126. Memory-Induced Tool-Drift in LLM Agents

     Mahavir Dabas, Jihyun Jeong, Ming Jin, Ruoxi Jia

127. Meta-Harness: Post-Training Reliable Agent Systems via Harness Search

     Yoonho Lee, Roshen Sanjay Nair, Qizheng Zhang, Kangwook Lee, Omar Khattab, Chelsea Finn

128. Minibinder Lab: The Reliability Gap Of Agents For Designing High Quality Protein Binders

     Anda-Raluca Epure, Deepa Mal Korani, Jonathan G. Hedley, Maxim Secor, Alejo Nevado-Holgado, Philip Torr

129. MIRAGE: A Polarity-Flipping Encoding Subspace in LLM Agents

     Pratibha Revankar, Kargi Chauhan, Jihye Kim, Sadiba Nusrat Nur, Vincent Siu, Chenguang Wang

130. Mitigating Over-Personalization in Language Models via Structured Memory

     Hakeem Hannoon, Andrew Zhao, Mihir Narayan, Sharvin Goyal, Ivaxi Sheth

131. Mitigating Visual Hallucinations for Reliable Multimodal Agents

     Sohyeon Kim, Sang Yeon Yoon, Kyeongbo Kong

132. MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents

     Lawrence Keunho Jang, Andrew Keunwoo Jang, Jing Yu Koh, Ruslan Salakhutdinov

133. NEST: Nascent Encoded Steganographic Thoughts

     Artem Karpov

134. Network-Level Prompt and Trait Leakage in Local Research Agents

     Hyejun Jeong, Mohammadreza Teymoorianfard, Abhinav Kumar, Amir Houmansadr, Eugene Bagdasarian

135. NitroBox: Lightning-Fast Sandbox for Large-Scale RL Training

     Yuzhou Nie, Ruilin Zhou, Zhaorun Chen, Jingyang Zhang, Yan Shao, Hongwei Li, Bo Li, Dawn Song, Wenbo Guo

136. Noticing the Watcher: LLM Agents Can Infer CoT Monitoring from Blocking Feedback

     Thomas Jiralerspong, Flemming Kondrup, Yoshua Bengio

137. Odysseys: Benchmarking Web Agents on Realistic Long Horizon Tasks

     Lawrence Keunho Jang, Jing Yu Koh, Daniel Fried, Ruslan Salakhutdinov

138. Omission Constraints Decay While Commission Constraints Persist in Long-Context LLM Agents

     Yeran Gamage

139. One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue

     Xinjie Shen, Rongzhe Wei, Peizhi Niu, Haoyu Peter Wang, Ruihan Wu, Eli Chien, Bo Li, Pin-Yu Chen, Pan Li

140. Online Boundary-Aware Memory for Case-Based Reasoning Agents

     Zheng Dong, Luming Shang

141. Open-World Evaluations for Measuring Frontier AI Capabilities

     Sayash Kapoor, Peter Kirgis, Andrew Schwartz, Stephan Rabanser, J.J. Allaire, Rishi Bommasani, Harry Coppock, Magda Dubois, Gillian K Hadfield, Andrew B. Hall, Sara Hooker, Seth Lazar, Steve Newman, Dimitris Papailiopoulos, Shoshannah Tekofsky, Helen Toner, Cozmin Ududec, Arvind Narayanan

142. OpenSeeker: Democratizing Frontier Search Agents by Fully Open-Sourcing Training Data

     Yuwen Du, Rui Ye, Shuo Tang, Xinyu Zhu, Yijun Lu, Yuzhu Cai, Siheng Chen

143. Out-of-Distribution Generalization of Risk Aversion in Language Models

     Kristina Zhang, Junior Chinomso Okoroafor, Benjamin Maltbie, Andrew Lin, Abhitej Bokka, Elliott Thornley

144. Oversight is Not Compliance: Tacit Collusion in LLM Pricing Agents Under Antitrust Regulation

     Meiri Anto, Juan J Vazquez

145. Parameters as Agentic Memory: Internalizing Long-Horizon Memories for Efficient LLM Agents

     Zhenheng Tang, Fanjunduo Wei, Zichen TANG, Peijie Dong, Xiang Liu, Qian Wang, Xiaowen Chu, Bo Li

146. Peer-Preservation in Frontier Models

     Yujin Potter, Nicholas Crispino, Vincent Siu, Chenguang Wang, Dawn Song

147. Plausible Deniability Guarantees for Whistleblowers

     Leo Richter, Matt J. Kusner

148. Position: LLM Social-Simulation Agents in the Wild Cannot Serve as Social Scientific Evidence Without an Identification Strategy

     Zezheng Lin, Fengming Liu

149. Position: Stop Hardcoding Multi-Agent Workflows That General Agents Will Outgrow

     Xisen Wang

150. ReCode: Unify Plan and Action for Universal Granularity Control

     Zhaoyang Yu, Jiayi Zhang, Huixue Su, Yufan Zhao, Yifan Wu, Mingyi Deng, Jinyu Xiang, Yizhang Lin, Fanqi Kong, Lingxiao Tang, Yuyu Luo, Bang Liu, Chenglin Wu

151. Red-Teaming Agent Execution Contexts: Open-World Security Evaluation on OpenClaw

     Hongwei Yao, Yiming Liu, Yiling He, Bingrun Yang

152. Reliable to Expressive: A Curriculum for Rubric-Following Safety Judges

     YongTaek Lim, hyeji choi, Minwoo Kim

153. Remote Control: AI Control with User Actions

     Jou Barzdukas, Matthew Nguyen

154. RevengeBench: Reverse Engineering Code-Space Policies from Behavioral Experiments

     Babak Rahmani, Sebastian Dziadzio, Joschka Strüber, Sergio Hernández-Gutiérrez, Matthias Bethge

155. Reward Bias Substitution: Single-Axis Bias Mitigations Redirect Optimization Pressure

     Max Lamparth, Daniel Fein, Andreas Haupt, Marcel Hussing, Mykel Kochenderfer

156. Reward Hacking in Rubric-Based Reinforcement Learning

     Anas Mahmoud, MohammadHossein Rezaei, Zihao Wang, Anisha Gunjal, Bing Liu, Yunzhong He

157. Robust Multi-Agent LLMs under Byzantine Faults

     Haejoon Lee, Vincent-Daniel Yun, Hyeonho Oh, Dimitra Panagou, Sai Praneeth Karimireddy

158. SAFARI: Scaling Long Horizon Agentic Fault Attribution via Active Investigation

     Chenyang Zhu, Jiayu Yao, Kushal Chawla, Youbing Yin, Nathan Wolfe, Pengshan Cai, Jingyu Wu, Spencer Hong, Sangwoo Cho, Shi-Xiong Zhang, Daben Liu, Sambit Sahu, Erin Babinsky

159. Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies

     Mumuksh Tayal, Manan Tayal, Ravi Prakash

160. Safe Under Budget? Verification Budgets and Abstention Failures in Web Agents

     Daoyuan Li

161. SafeClawBench: An Operating-System Perspective on Evaluating the Security of Claw-like Agent Systems

     Peizhi Niu, Shangding Gu, Wenjie Qu, Tianneng Shi, Yuankai Li, Ahmad Tawaha, Hend Alzahrani, Vincent Siu, Boyi Li, Chenguang Wang, Jiaheng Zhang, Basel Alomair, Ming Jin, Muhao Chen, Chi Wang, Costas Spanos, Dawn Song

162. Same Action, Different Justification: Path-Based Authorization for Irreversible Agent Actions

     Jungsoo Baek

163. Same Biology, Different Scores: Quantifying the Tool-Use Confound in Agentic Biology Evaluation

     Alyssia Jovellanos, Martin Ciesielski-Listwan

164. Scaling Laws for Strategic Interactions

     Joie Zhang, Danqi Chen, Peter Henderson, Lewis Hammond

165. Sell Me This Stock: Unsafe Recommendation Drift in LLM Agents

     Zekun Wu, Adriano Koshiyama, Sahan Bulathwela, Maria Perez-Ortiz

166. SkillOptimizer: Agent Skill Optimization Through Subskills Without Task Supervision

     Nicholas Crispino, Shubham Gaur, Xuefang Yang, Angela Yu, Berat Ercevik, Clara Sapugay, Yujin Potter, Dawn Song, Chenguang Wang

167. SlotGuard: Stop Oversharing Private Local Context in LLM Agent Transcripts

     Haocheng Xia, Yongjoo Park

168. Smarter Saboteurs, Better Fixers: Scaling & Security in Linear Multi-Agent Workflows

     Timothy McAllister, Sina Abdidizaji, Ivan Garibay, Ozlem Garibay

169. Sockpuppetting: Jailbreaking LLMs by Combining Prefilling with Optimization

     Asen Dotsinski, Panagiotis Eustratiadis

170. SRTJ: Self-Evolving Rule-Driven Training-Free LLM Jailbreaking

     Jindong Li, Ying Liu, Yali Fu, Jinjing Zhu, Leyao Wang, Menglin Yang, Rex Ying

171. Steering Externalities: Benign Activation Steering Unintentionally Increases Jailbreak Risk for Large Language Models

     Chen Xiong, Zhiyuan He, Pin-Yu Chen, Ching-Yun Ko, Tsung-Yi Ho

172. Stop Comparing LLM Agents Without Disclosing the Harness

     Yunbei Zhang, Janet Wang, Yingqiang Ge, Weijie Xu, Jihun Hamm, Chandan K. Reddy

173. Stop Reporting System-Level AI Reasoning as Individual Model Capability

     Adhiraj Chhoda

174. Structured Hallucination in Tool-Using Agents: Measuring and Mitigating LLM Synthesis Corruption in Production

     Tung Thanh Hoang

175. SudoBench: A Contextual Authorization Benchmark for LLM Agents

     Vincent Siu, Tianneng Shi, Shangding Gu, Zhun Wang, Dawn Song, Chenguang Wang

176. Temper and Tilt Lead to SLOP: Reward Hacking Mitigation with Inference-Time Alignment

     Ye Wang, Jing Liu, Toshiaki Koike-Akino

177. Terminal Agents Suffice for Enterprise Automation

     Patrice Bechard, Orlando Marquez Ayala, Emily Chen, Jordan Skelton, Sagar Davasam, Srinivas Sunkara, Vikas Yadav, Sai Rajeswar

178. The Best-Laid SCHEMEs: Coordinated Sabotage and Monitoring in Multi-Agent Systems

     Nikolay Radev, Lennart J Haas, Benjamin Arnav, Pablo Bernabeu-Perez

179. The Monitorability Gap Between Reasoning in Thinking and Reasoning in the Output

     Zora Che, David Lindner

180. The Safety Illusion of Greedy Decoding: Diagnosing Booster's Compliant Leakage and a Phase-2 Mitigation

     Tung Lam Tran, Muhammad Rifki Kurniawan, Christopher Kanan

181. The Token Tax : Measuring the Diminishing Returns of Test-Time Compute in Agentic Pipelines

     Kushagra Agrawal, Christian Beecks, Man-Fai Leung

182. Thought Virus: Spreading Subliminal Biases in Multi-Agent Systems

     Moritz Weckbecker, Jonas Müller, Ben Hagag, Michael Mulet

183. Tool Selection Bias Amplifies in Multi-turn User–Agent Interactions

     Nakyeong Yang, Junseok Kim, Kyomin Jung

184. Tool-Framing Bypasses LLM Safety: Procedural Abstraction Reduces Refusal Rates by Up to 40 Percentage Points Across Models

     Kevin Power

185. ToolFailBench: Diagnosing Tool-Use Failures in LLM Agents

     Harsh Soni

186. Toward Scalable Terminal Task Synthesis via Skill Graphs

     Zhiyuan Fan, TingHao YU, Yuanjun Cai, JiangTaoGuan, Yun Yang, Dingxin Hu, Jiang Zhou, Xing W, Zhuo Han, feng zhang, Lilin Wang

187. Towards Budget-Aware Agents: Do LLM Agents Know What They Will Spend?

     Yuxiang Lin, Zihan Wang, Mengyang Liu, Yuxuan Shan, Longju Bai, Junyao Zhang, Xing Jin, Boshan Chen, Jinyan Su, Xingyao Wang, Jiaxin Pei, Manling Li

188. Towards Predictive Models of Strategic Behaviour in Large Language Model Agents

     Jennifer Za, Aristeidis Panos, Jan Cuhel

189. TRACE: Capability-Targeted Agentic Training

     Hangoo Kang, Tarun Suresh, Jon Saad-Falcon, Azalia Mirhoseini

190. TraceSafe: A Systematic Assessment of LLM Guardrails on Multi-Step Tool-Calling Trajectories

     Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen

191. Tracking the Behavioral Trajectories of Adapting Agents

     Jonah Leshin, Manish Shah, Ian Timmis

192. Tracking the Truth: Object-Centric Spatio-Temporal Monitoring for Video Large Language Models

     Tri Cao, Khoi M. Le, Thong Thanh Nguyen, Cong-Duy T Nguyen, Quynh Vo, Anh Tuan Luu, Chunyan Miao, See-Kiong Ng, Shuicheng YAN, Bryan Hooi

193. Training Language Agents to Learn from Experience

     Yuval Shalev, Zifeng Ding, Mateja Jamnik

194. Training ML Models with Predictable Failures

     Will Schwarzer, Scott Niekum

195. Untrusted Content Masking for Web Agents with Security Guarantees

     Kristina Nikolić, Egor Zverev, Javier Rando, Matthew Jagielski, Edoardo Debenedetti, Florian Tramèr

196. VATS: Exploiting Implicit Authority in Error-Path Injection via Systematic Mutation

     Harshil Patel, Kunal Pai

197. VIGIL: A Reflective Runtime for Self-Healing LLM Agents

     Christopher Cruz

198. WARD: Adversarially Robust Defense of Web Agents Against Prompt Injections

     Tri Cao, Yulin Chen, Thanh Hieu Cao, Yibo Li, Khoi M. Le, Thong Thanh Nguyen, Yuexin Li, Yufei He, Yue Liu, Shuicheng YAN, Bryan Hooi

199. WARP: A Wrapper-Based, Adaptive, Realistic Pipeline for Reliable Web-Agent Robustness Testing

     Jasmine Xinze Li, Ashton Chew, Maxwell Lin, Eliot Krzysztof Jones, Xiaohan Fu, Andy Zou

200. We Let Agents Compete and They Tried to Cheat. KernelGuard:Defending GPU Competitions from Adversarial Agentic Systems

     Muhammed Emin Baslak, Erik Schultheis, Matej Sirovatka, Mark Saroufim, Alex L Zhang

201. Web Agents Leak Sensitive Data on Simple Scalable Websites

     Zachary Yahn

202. WebAgentGuard: A Reasoning-Driven Guard Model for Detecting Prompt Injection Attacks in Web Agents

     Yulin Chen, Tri Cao, Haoran Li, Yibo Li, Yue Liu, Yufei He, Khoi M. Le, Yangqiu Song, Shuicheng YAN, Bryan Hooi

203. WebArena-Pro: A Heterogeneous, Multimodal, Reproducible Benchmark for Web Agents

     Imene Kerboua, Fatemeh Pesaran zadeh, Xing Han Lù, Weijian Qi, Alexander Miller, Junyi Song, Yunjia Tian, Dongjin Kang, Seyeon Choi, Marzia Nouri, Ewen Gueguen, Matteo Boglioni, Fengyuan Liu, Zeyi Liao, Mengqi Yuan, Yue Li, Alexandre Lacoste, Alexandre Drouin, Spandana Gella, Huan Sun, Gunhee Kim, Siva Reddy

204. WebPII: Benchmarking Visual PII Detection for Computer-Use Agents

     Nathan J. Zhao

205. What Can One Bad Tool Call Destroy? Measuring and Minimizing Blast Radius in Agentic Tool Use

     Muhammet Anil Yagiz

206. What Game-Theoretic Benchmarks Miss: Strategic Silence in Multi-Agent LLMs

     Jerick Shi, Terry Jingchen Zhang, Vincent Conitzer, Zhijing Jin

207. When Cloud Agents Meet Device Agents: Lessons from Hybrid Multi-Agent Systems

     Corrado Rainone, Davide Belli, Bence Major, Arash Behboodi

208. When Do Covert Channels Emerge? Probing Steganographic Capacity in Multimodal Agents via Diffusion VAE Latents

     Catherine Ge-Wang, Tushar Nagar, Joy Zheyun Yang

209. When Reasoning Traces Become Performative: Step-Level Evidence that Chain-of-Thought Is an Imperfect Oversight Channel

     Wenkai Li, Fan Yang, Ananya Hazarika, Shaunak A. Mehta, Koichi Onoue

210. Who Flips? Self- and Cross-Model Counterarguments Reveal Answer Instability in LLMs

     Nafiseh Nikeghbal, Amir Hossein Kargaran, Shaghayegh Kolli, Jana Diesner

211. Widening the Gap: Exploiting LLM Quantization via Outlier Injection

     Xiaohua Zhan, Kazuki Egashira, Robin Staab, Mark Vero, Martin Vechev

212. WinDOM: Self-Family Distillation for Small-Model GUI Grounding

     Chengheng Li Chen, Zhiqian Zhou, Hao Chen, Nicolas Chauvin

213. Within-Episode Failure Recovery in LLM Agents via Progress-Gated Dual-Process Routing

     Ankush Kadu, Aswanth Krishnan

214. WorldFork: Trace-Auditable Forecasting Agents in Open-Ended Domains

     Hanson Wen, James Gui

215. Your Agent, Their Asset: A Real-World Safety Analysis of OpenClaw

     Zijun Wang, Haoqin Tu, Letian Zhang, Hardy Chen, Juncheng Wu, Xiangyan Liu, Zhenlong Yuan, Tianyu Pang, Michael Qizhe Shieh, Fengze Liu, Zeyu Zheng, Huaxiu Yao, Yuyin Zhou, Cihang Xie

216. Your Cursor is Not Secure: Command Line Interface Agent Can Expose Realistic Risks Through Tactics, Techniques, and Procedures

     Weidi Luo, Qiming Zhang, Tianyu Lu, Xiaogeng Liu, Bin Hu, CHIU Hung Chun, Siyuan Ma, Yizhe Zhang, Xusheng Xiao, Yinzhi Cao, Zhen Xiang, Chaowei Xiao