Tag
该论文研究 Verus/Rust 形式验证工作流中，正确性反馈如何反而抑制规格完整性审计所需的证据，发现独立无反馈探索比带纠正反馈的循环产生多一倍的认证反例，并在 NeurIPS 2026 AI for Verifiable Coding 工作坊被接收。
This paper formalizes four concurrency anomalies in multi-agent LLM systems, mechanically verifies a consistency hierarchy, and provides verified Rust runtimes with bounded prevention costs, including a fix for ByteDance's deer-flow and tool-effect reordering in LangGraph.