AI RESEARCH
The Causal Impact of Tool Affordance on Safety Alignment in LLM Agents
arXiv CS.AI
•
ArXi:2603.20320v1 Announce Type: cross Large language models (LLMs) are increasingly deployed as agents with access to executable tools, enabling direct interaction with external systems. However, most safety evaluations remain text-centric and assume that compliant language implies safe behavior, an assumption that becomes unreliable once models are allowed to act.