arXiv Machine Learning June 2, 2026 By Mohammed Sameer Syed (University of Arizona), Rozhin Yasaei (University of Arizona)

Same Payload, Different Channel: Measuring Trust Asymmetry in Tool-Using Language Models

Read the original on arXiv Machine Learning →

arXiv:2606. 00566v1 Announce Type: new Abstract: As language models take on agentic roles that span calling external APIs, reading tool outputs, and acting on instructions embedded in third-party content, their attack surface expands well beyond what users type.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

arXiv AI

Jun 19

The Autonomy Tax: Defense Training Breaks LLM Agents

arXiv:2603. 19423v2 Announce Type: replace-cross Abstract: Large language model (LLM) agents increasingly rely on external tools (file operations, API calls, database transactions) to autonomously complete complex multi-step tasks.

By Shawn Li, Yue Zhao

llms agents benchmarks safety

arXiv Machine Learning

Sep 2

AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes

arXiv:2609.00052v1 Announce Type: cross Abstract: Commercial LLM APIs advertise a specific foundation model, but the served backbone may be silently substituted, quantized, or wrapped, for example to...

By Xun Wang, Bihe Zhao, Michael Backes, Franziska Boenisch, Adam Dziedzic

llms agents efficiency

arXiv AI

Aug 24

Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification

The paper identifies a vulnerability in large language models where harmful intent can be hidden within benign narratives, a phenomenon termed Semantic Camouflage. By examining latent activation patterns across several small language model families, the authors discover an "Intent Horizon"—a layer depth where harmful intent representations collapse. They propose Latent Intent Verification (LIV), a lightweight probing defense that detects harmful intent in early layers and outperforms existing guardrails on the PKU-SafeRLHF dataset.

By Md. Hasib Ur Rahman

llms safety

arXiv AI

Aug 3

Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

arXiv:2607. 29254v1 Announce Type: new Abstract: AI agents extend large language models (LLMs) with external tools, enabling them to perform complex tasks and translate model outputs into consequential real-world actions.

By Minghui Pan, Jiayuxuan Yang, Yuanyuan Yuan, Yu Jiang, Zhenpeng Chen

llms agents benchmarks safety

arXiv AI

3d ago

Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents

arXiv:2609.39065v1 Announce Type: cross Abstract: LLM agents increasingly rely on installable skills, which are packages of instructions, code, and resources that equip them with task-specific capabi...

By Yan Wang, Zhihao Zhang, Ke Chen, Kai Chen, Yaqin Zhang, Duohe Ma, Jun Dai, Xiaoyan Sun

llms agents

arXiv AI

Jun 18

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents

arXiv:2606. 18356v1 Announce Type: cross Abstract: Tool-using language-model agents introduce security failures that go beyond unsafe text: they can disclose protected objects, write persistent memory, send messages, modify databases, or trigger harmful code and tool effects.

By Yuchuan Tian, Mengyu Zheng, Haocheng Mei, Ye Yuan, Chao Xu, Xinghao Chen, Hanting Chen, Yu Wang

llms agents benchmarks safety

One email a morning, machine-written

Related stories

The Autonomy Tax: Defense Training Breaks LLM Agents

AgentProv: Auditing Agentic LLM API Providers via Tool-use Policy Probes

Truth Lies Deep: Countering Semantic Camouflage via Latent Intent Verification

Tool Specifications Matter: Uncovering and Mitigating Safety Risks in AI Agents

Can Agents Trust Their Skills? Uncovering Unsafe Chains of Trust in Skill-Based LLM Agents

SafeClawBench: Separating Semantic, Audit-Evidence, and Sandbox Harm in Tool-Using LLM Agents