Live intelligence

Latest AI updates

1 updates
Research

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

Researchers introduce Soteria, a framework for LLM agents that performs multi-step tool calls while satisfying both task completion and domain policy conformance. Before execution, the agent generates a structured plan that is formally verified against specifications prior to any tool invocation; during execution, the verified plan constrains trajectories and guides recovery when unsafe actions are blocked. The authors report 1.7 times the average task success rate of the best baselines across multiple tool-use benchmarks, with no policy specification violations.

SoteriaLLM agentsformal verification