arXiv AI August 11, 2026 By Satoshi Matsuoka

Compositional Threat Analysis of Latent Compromise in LLM Agent Systems: The Order 66 Scenario

arXiv:2608. 08131v1 Announce Type: cross Abstract: In the fictional Order 66, catastrophe does not arise from a powerful command alone: a trusted population is preconditioned, a short directive activates the concealed condition, and protective authority turns against the system.

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

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 9

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

arXiv:2606. 09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.

By Xiaofeng Lin, Yukai Yang, Daniel Guo, Sahil Arun Nale, Charles Fleming, Guang Cheng

llms agents benchmarks safety

Hugging Face Trending Papers

Jun 8

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

Tool-using LLM agents interact with the world through actions that persist state in artifacts (e. g.

llms agents benchmarks safety

arXiv Machine Learning

Jun 17

Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems

arXiv:2606. 17182v1 Announce Type: new Abstract: Multi-agent LLM systems share state through memory stores, vector indices, and tool registries.

By Sajjad Khan

llms agents

arXiv AI

Jul 23

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

arXiv:2607. 19449v1 Announce Type: cross Abstract: Evaluation frameworks for tool-augmented LLM agents focus overwhelmingly on capability metrics or explicit tool crashes, leaving silent infrastructure failures and HTTP 200 responses with empty, null, or malformed payloads largely unaudited.

By Aarushi Singh

llms agents benchmarks safety

arXiv AI

Jul 21

STAC: When Innocent Tools Form Dangerous Chains for LLM Agents

arXiv:2509. 25624v3 Announce Type: replace-cross Abstract: As LLMs advance into autonomous agents with tool-use capabilities, they introduce security challenges that extend beyond traditional content-based LLM safety concerns.

By Jing-Jing Li, Jianfeng He, Chao Shang, Devang Kulshreshtha, Xun Xian, Yi Zhang, Hang Su, Sandesh Swamy, Yanjun Qi

llms agents multimodal benchmarks safety

Related stories

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

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

Context-Fractured Decomposition Attacks on Tool-Using LLM Agents: Exploiting Artifact Provenance Gaps

Verified Detection and Prevention of Concurrency Anomalies in Multi-Agent Large Language Model Systems

Guardrails as Scapegoats: Auditing Unfaithful Safety Refusals in Tool-Augmented LLM Agents

STAC: When Innocent Tools Form Dangerous Chains for LLM Agents