AI Tools & Models HOTFeaturedAll
arXiv cs.AIScore75

Soteria: Formally Verified Planning with Runtime Enforcement for Safe LLM Agents

Summary

This work combines formal verification with runtime enforcement so multi-step tool-calling agents complete tasks without breaking domain rules.

Why this matters

Covers LLM and Agent · Relevant to this topic

Open original ↗

Source: arXiv cs.AI · arxiv.org

Topics

Related items