arXiv AI July 22, 2026 By Jie Li

Trusted Credentials, Untrusted Behavior: Benchmarking LLM-Agent Security in High-Performance Computing

arXiv:2607. 18485v1 Announce Type: cross Abstract: Large language model (LLM) agents are starting to take on routine work in high-performance computing (HPC), including monitoring Slurm jobs, diagnosing failed builds, inspecting simulation output, and coordinating scientific workflows.

Summary generated by The Flow from the publisher's feed. The full article lives at arXiv AI.

arXiv AI

Aug 5

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

arXiv:2608. 03499v1 Announce Type: new Abstract: Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations.

By Prince Zizhuang Wang, Aojie Yuan, Haiyue Zhang, Xiyang Hu, Yue Zhao, Shuli Jiang

agents benchmarks safety

arXiv AI

Jul 1

Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens

arXiv:2606. 30755v1 Announce Type: cross Abstract: Claw-like AI agents (e.

By Peizhi Niu, Wenjie Qu, Shangding Gu, 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

llms agents benchmarks safety

Hugging Face Trending Papers

Aug 4

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Recent advances in persistent personal-agent frameworks are making human-centered agent networks realistic deployment targets: each user can be served by an AI agent that acts on the user's behalf, maintains state, and communicates with other agents through social and task relations. In these networks, everyday tool use becomes multi-party owned-agent collaboration over personal workspaces, where files, records, tools, and policies are not directly visible across owners.

agents benchmarks safety

arXiv AI

Jun 10

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

arXiv:2606. 10749v1 Announce Type: cross Abstract: Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environments.

By Yuchen Ling, Shengcheng Yu, Zhenyu Chen, Chunrong Fang

llms agents benchmarks

arXiv AI

Jun 30

From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

arXiv:2606. 29073v1 Announce Type: cross Abstract: Model Context Protocol (MCP)-style ecosystems give language-model applications a practical connection layer for tools, resources, prompts, and transports.

By Ting Liu

agents benchmarks

arXiv AI

1d ago

Beyond Direct Access: Resource Hijacking in LLM Agents

arXiv:2608. 15108v1 Announce Type: cross Abstract: Large language model agents are increasingly connected to high-value resources such as computing infrastructure, credentials, usage budgets, identities, private knowledge, communication channels, and organizational workflows.

By Puyu Zeng, Qibing Ren

llms agents

Related stories

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Understanding and Evaluating Claw-like Agent Security Through a Computer-Systems Lens

WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks

Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation

From Tool Connection to Execution Control: Benchmarking Security Invariants in MCP-Style Agent Runtimes

Beyond Direct Access: Resource Hijacking in LLM Agents