提出LLMbda演算，用形式化方法建模AI代理对话中的信息流，理论深度与实用性兼备。
arXiv:2602.20064v2 Announce Type: replace-cross Abstract: Large language models are increasingly deployed as agents: they plan, call tools, read untru…
从理论层面形式化语言反馈学习，提供可证明的保证，为机器学习新范式奠定基础。
arXiv:2506.10341v2 Announce Type: replace Abstract: Interactively learning from observation and language feedback is an increasingly studied area driv…
用大模型驱动可靠的抽象解释，SAIL方法让静态分析兼顾精度与效率
arXiv:2511.13663v2 Announce Type: replace-cross Abstract: How to construct globally sound abstract interpreters to safely approximate program behavior…
新方法从代码规范自动推断正确性，无需运行即可验证，提升代码质量与可靠性。
arXiv:2605.29822v1 Announce Type: cross Abstract: Large language models (LLMs) have become integral to modern software development, enabling automated…
将安全智能体建模为递归程序孔洞，提供一种形式化保障AI行为安全的新思路。
arXiv:2605.28617v1 Announce Type: new Abstract: LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the …
为AI工作流架构提出效果透明治理框架，核心突破语义保持与可判定性边界，学术价值极高。
arXiv:2605.01030v3 Announce Type: replace Abstract: We present a machine-checked formalization of structurally governed AI workflow architectures and …
研究累积命题依赖逻辑中蕴涵问题的计算复杂度，揭示理论计算机科学前沿进展。
arXiv:2605.21113v1 Announce Type: cross Abstract: This paper establishes and proves complexity results for entailment for cumulative propositional dep…
让LLM代理通过可编程运行时技能，实现效率与准确性的双重提升。
arXiv:2605.19604v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills dete…
AI生成代码靠得住？形式化方法给出数学级别的安全保障，从此告别“测试不能证明没有bug”的焦虑。
Article URL: https://www.codemetal.ai/research/ai-generated-code-that-works-and-proves-it Comments URL: https://news.ycombinator.com/item?id=48186334 …
形式化方法与LLM结合，为AI系统合规提供审计、监控和干预的全生命周期治理方案。
arXiv:2605.16198v1 Announce Type: new Abstract: We examine one particular dimension of AI governance: how to monitor and audit AI-enabled products and…