Multi-Turn Intent Detection for LLM and Agent Security (ArXiv)

Multi-Turn Intent Detection for LLM and Agent Security (ArXiv)(arxiv.org)

1 points by sharathr 89 days ago | 1 comment

sharathr 89 days ago |

Hi HN — I’m one of the authors.

We’ve been working on security for multi-turn agent loops and noticed most detection approaches operate on isolated prompts. This paper introduces a framework for modeling intent trajectories across sequences in real time (<20ms), enabling enforcement before harmful actions occur.

Happy to answer technical questions or discuss assumptions in the paper.