不只看结果对错，用验证链思维评估LLM在Rust形式化验证中的真实推理能力，基准测试VCoT-Bench来了。
arXiv:2603.18334v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly assist secure software development, their abili…
用代数方法为AI智能体执行构建可信策略，7图10表+5算法，形式化框架扎实，值得深挖。
arXiv:2608.16402v1 Announce Type: new Abstract: Large language model-based agentic frameworks primarily optimize capability: whether an agent can reas…
面对变幻莫测的AI智能体，这份综述给出规范、验证、执行三层安全防线，是构建可信Agent的必读指南。
arXiv:2608.14590v1 Announce Type: new Abstract: LLM agents increasingly perform irreversible real-world actions, including database updates, API calls…
把形式化风险认证引入 LLM 安全代理，轨迹级保障让入侵检测更可信，开源模型实测见真章。
arXiv:2608.05199v1 Announce Type: cross Abstract: Autonomous security agents operate as staged pipelines, such as classifying network traffic and then…
用形式化方法验证业务规则一致性，让规则冲突在运行前无所遁形。
arXiv:2608.00396v1 Announce Type: cross Abstract: Maintaining consistency between natural language documentation of business rules and their evolving …
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…
提出4/δ界限，为LLM验证器系统提供形式化保证，破解可预测性难题，值得关注。
arXiv:2512.02080v3 Announce Type: replace Abstract: The integration of Formal Verification tools with Large Language Models (LLMs) offers a path to sc…
用大模型把形式化验证从玩具级带到大型系统，这套自动组合推理框架值得一看。
arXiv:2604.11556v2 Announce Type: replace-cross Abstract: LLM-assisted software development has become increasingly prevalent, and can generate large-…
一篇论文提出了图概率模型来形式化LLM原生软件系统中的生成流，为开发者提供了可解释的定量分析框架。
arXiv:2606.15943v1 Announce Type: cross Abstract: Engineering LLM-native software remains a challenging and immature field. Current practice is largel…
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…