Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents
arXiv:2610.28982v1 Announce Type: new Abstract: While large language models are increasingly deployed as tool-calling agents, their safety evaluations still focus primarily on their ability to refuse harmful requests in text. We investigate whether the refusal behavior in text transfers to tool use…
Read the full story at arXiv cs.AI ↗
Timeline · 1 report
- 2026-10-22 04:00 · arXiv cs.AI
Behavior Beyond Text: Evaluating Refusal Transfer Failure in LLM Agents