Tag
GitHub Next 与微软研究院推出 Chopin 和 Proof-Driven Development Kit（PDD Kit），可将开发计划转化为形式化规范，并证明 AI 生成的代码对所有输入均符合规范，使团队无需逐行审查即可将 AI 生成的代码安全上线，目前已进入研究预览阶段。
The paper formalizes Spec-Driven Agentic Development (SDAD) to restructure the software development lifecycle with AI, emphasizing precise specifications and multi-agent verification for disciplined agentic speed.
SCP-NL2TL is a paper proposing a selective translation framework that uses conformal risk control to decide when natural language to temporal logic translations can be trusted, improving reliability for safety-critical autonomous systems.
HyPOLE introduces a framework for multi-agent reinforcement learning under partial observability that uses hyperproperty-guided learning via HyperLTL temporal logic, integrated with centralized training for decentralized execution, and demonstrates improvements over baselines on SMAC, MessySMAC, and WildFire benchmarks.
Discusses the need for formal specifications in AI-generated code and introduces PICK, a tool that leverages human judgment to help programmers specify desired properties for LLM-generated regular expressions.