INTENT-AS-A-TOOL Makes it Easy to Track Agentic Misalignment

The paper introduces INTENT-AS-A-TOOL, a method that equips large language models with intent-targeted tools to provide a fine-grained, judge‑free signal of their commitment to specific behaviors during reasoning. By monitoring the probability of calling these intent tools, the authors can track how intent evolves throughout generation, complementing chain‑of‑thought monitoring and expanding post‑hoc labels into dense trajectories. The approach identifies critical steps for online intervention, demonstrating that action preferences are useful for detecting agentic misalignment in autonomous agents.

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 Computation and Language.

• llms
• agents
• safety