arXiv AI
Representation Transitions Reveal Emerging Safety Risks in Multi-Turn LLM Agents
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jul 14
When Local Monitors Miss Compositional Harm: Diagnosing Distributed Backdoors in Multi-Agent Systems
arXiv:2607. 11751v1 Announce Type: cross Abstract: As multi-agent, tool-using LLM systems are deployed, a common safety net is a runtime monitor that checks each message, tool call, or step on its own.
arXiv AI
Jul 29
Early Detection of Distributed Backdoors in Multi-Agent LLM Systems: A Characterization Study
arXiv:2607. 24893v1 Announce Type: cross Abstract: Multi-agent LLM systems can be attacked by a payload that no single agent ever holds in full: a poisoned tool hides encrypted fragments in its observations, spreads them across several agents, and an external step reassembles and executes them after the run.
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.
arXiv Computation and Language
2d ago
The Geometry of Harmfulness in Multi-Turn Attacks
arXiv:2609.38389v1 Announce Type: cross Abstract: Large language models (LLMs) remain vulnerable to adversarial attacks that circumvent safety alignment to elicit harmful outputs. It remains unclear...
arXiv AI
Jul 3
Distributed Attacks in Persistent-State AI Control
arXiv:2607. 02514v1 Announce Type: new Abstract: As AI coding agents become more autonomous, they increasingly ship code iteratively, with the codebase persisting across sessions.
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.