InfoResearchPreprintLLM-specific
Monitor-Validity Failures: LLM Safety Evidence Paths at Evolving Framework Boundaries
- Published
- Record updated
Summary
This paper studies monitor-validity failures in LLM and agent frameworks, where a safety detector recognizes a policy-relevant payload but the framework never routes that evidence to its enforcement decision. Using canary contracts on public framework repairs, the authors confirm 18 evidence-path failures across 11 LLM or agent safety project groups and four implementation ecosystems, with 14 reaching enforcement boundaries. They conclude that monitor assumptions need regression tests at the schemas, streams, tools, and adapters that frameworks evolve.
Mitigation
Monitor assumptions need regression tests at the schemas, streams, tools, and adapters that frameworks evolve.