AI RESEARCH
GSAR: Typed Grounding for Hallucination Detection and Recovery in Multi-Agent LLMs
arXiv CS.AI
•
ArXi:2604.23366v1 Announce Type: new Autonomous multi-agent LLM systems are increasingly deployed to investigate operational incidents and produce structured diagnostic reports. Their trustworthiness hinges on whether each claim is grounded in observed evidence rather than model-internal inference. Existing groundedness evaluators (binary classifiers, LLM-as-judge scalars, self-correction loops) treat ing evidence as interchangeable and emit a single signal that offers no principled control over downstream action.