AI RESEARCH
TraceFix: Repairing Agent Coordination Protocols with TLA+ Counterexamples
arXiv CS.AI
•
ArXi:2605.07935v1 Announce Type: new We present TraceFix, a verification-first pipeline for Large Language Model (LLM) multi-agent coordination. An agent synthesizes a protocol topology as a structured intermediate representation (IR) from a task description, generates PlusCal coordination logic, and iteratively repairs the protocol using counterexamples from the TLA+ model checker (TLC) until verification succeeds. Verified process bodies are compiled into per-agent system prompts and executed under a runtime monitor that rejects out-of-topology coordination operations.