arXiv AI

Revealing Safety-Critical Scenarios for UTM via Transformer

arXiv:2606. 31114v1 Announce Type: new Abstract: Unmanned Traffic Management (UTM) systems are cloud-based platforms designed to manage and coordinate multiple aerial vehicles remotely.

arXiv AI

Jun 16

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

arXiv:2605. 11047v2 Announce Type: replace-cross Abstract: Agentic language-model systems increasingly rely on mutable execution contexts, including files, memory, tools, skills, and auxiliary artifacts, creating security risks beyond explicit user prompts.

By Hongwei Yao, Yiming Liu, Yiling He, Bingrun Yang

agents robotics benchmarks safety

arXiv Machine Learning

Jun 26

NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing

arXiv:2603. 19864v2 Announce Type: replace Abstract: Penetration testing, the practice of simulating cyberattacks to identify vulnerabilities, is a complex sequential decision-making task that is inherently partially observable and features large action spaces.

By Raphael Simon, Jos\'e Carrasquel, Wim Mees, Pieter Libin

reinforcement-learning efficiency

arXiv AI

Jun 12

Unsafer in Many Turns: Benchmarking and Defending Multi-Turn Safety Risks in Tool-Using Agents

arXiv:2602. 13379v2 Announce Type: replace-cross Abstract: LLM-based agents are becoming increasingly capable, yet their safety lags behind.

By Xu Li, Simon Yu, Minzhou Pan, Yiyou Sun, Bo Li, Dawn Song, Xue Lin, Weiyan Shi

llms agents multimodal benchmarks safety

arXiv AI

2d ago

Hierarchical Agentic Incident Response with Digital-Twin-Validated Attack Inference

arXiv:2608. 15016v1 Announce Type: cross Abstract: Network incident response remains slow and labor-intensive as the defender must infer multi-stage attacks from partial observations and translate recovery decisions into reliable system commands.

By Yiran Gao, Juntao Chen, Tao Li

llms agents fine-tuning

arXiv AI

Aug 11

AIVV: Neuro-Symbolic LLM Agent-Integrated Verification and Validation for Trustworthy Autonomous Systems

arXiv:2604. 02478v2 Announce Type: replace Abstract: Deep learning models excel at detecting anomaly patterns in normal data.

By Jiyong Kwon, Ujin Jeon, Sooji Lee, Guang Lin

llms agents

arXiv AI

Jul 14

Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming

arXiv:2607. 11698v1 Announce Type: cross Abstract: Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable.

By Xutao Mao, Xiang Zheng, Cong Wang

llms agents benchmarks safety

arXiv AI

3d ago

Coverage Aware Active Evaluation for Failure Discovery with Paired Systems

arXiv:2608. 13719v1 Announce Type: new Abstract: Autonomous systems can fail in rare and heterogeneous ways, making real-world failure discovery difficult under limited testing budgets.

By Anjali Parashar, Rachel Luo, Apoorva Sharma, Sushant Veer, Edward Schmerling, Carson Sobolewski, Mingxin Yu, Chuchu Fan, Marco Pavone

agents robotics

arXiv Machine Learning

Jul 28

Diffusion-Guided Search via Exponential Tilting (DiffTilt): An Application to Falsification of Safety-Critical Systems

arXiv:2607. 23134v1 Announce Type: new Abstract: Discovering rare safety-critical failures in autonomous and cyber-physical systems is a fundamental challenge in verification and validation.

By Tanmay Khandait, Preetom Biswas, Hideki Okamoto, Bardh Hoxha, Georgios Fainekos, Giulia Pedrielli

agents diffusion benchmarks safety

arXiv AI

Jun 2

SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents

arXiv:2606. 02302v1 Announce Type: cross Abstract: Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services.

By Hao Cheng, Changtao Miao, Tianle Song, Yin Wu, He Liu, Erjia Xiao, Junchi Chen, Xiaoyu Shi, Yichi Wang, Jing Yang, Taowen Wang, Jinhao Duan, Mengshu Sun, Peiyan Dong, Xuan Shen, Yang Cao, Renjing Xu, Kaidi Xu, Jindong Gu, Bo Zhang, Jize Zhang, Chenhao Lin, Philip Torr, Chao Shen

llms agents benchmarks safety

arXiv Machine Learning

Jun 26

Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation

arXiv:2509. 20008v2 Announce Type: replace Abstract: Penetration testing, the simulation of cyberattacks to identify security vulnerabilities, presents a sequential decision-making problem well-suited for reinforcement learning (RL) automation.

By Raphael Simon, Pieter Libin, Wim Mees

reinforcement-learning benchmarks

arXiv AI

Aug 11

ActBench: Self-Evolving Benchmark of Behavioral Safety in Cowork Agents

arXiv:2608. 09476v1 Announce Type: cross Abstract: Cowork agents may complete benign tasks while disclosing protected data, manipulating unauthorized state, invocate unauthorized API.

By Hongwei Yao, Yiming Liu, Meihui Chen, Jieling Chen, Zikun Chen, Yiling He, Wangze Ni, Cong Wang, Kui Ren

llms agents benchmarks safety

Hugging Face Trending Papers

Jul 13

Agent Hacks Agent: Autoresearch for Production-Agent Red-Teaming

Production LLM agents such as Claude Code and Codex operate over untrusted content, files, commands, and workspace state, making safety failures directly actionable. Red-teaming must therefore keep pace with evolving models and tools.

llms agents benchmarks safety

Related stories