MAGS驗證智能體代碼

Computer Science > Artificial Intelligence arXiv:2609.

19391 (cs) [Submitted on 16 Sep 2026] Title:MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs Authors:Albert Wu, Nicholas Roberts, Tzu-Heng Huang, Haoran Lin, Gil Friedman, Sungjun Cho, Gabriel Orlanski, Frederic Sala View a PDF of the paper titled MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs, by Albert Wu and 6 other authors View PDF HTML (experimental) Abstract:LLM coding agents now generate complex programs at a scale that makes thorough human review increasingly difficult, raising the risk of safety and security failures.

Common approaches, including fuzz testing, static analysis, and LLM-as-a-Verifier, can detect many failures but struggle to cover all possible edge cases.

Formal verification addresses this by providing machine-checkable guarantees over specified properties, but traditionally demands substantial manual specification and proof engineering.

We introduce a unified multi-agent framework, MAGS, that generates executable programs with formal safety guarantees, using Dafny as a verification-aware intermediate representation where safety properties can be mechanically checked.

MAGS formalizes and freezes human-audited APIs and safety requirements, translates generated code into Dafny, repairs violations using verifier feedback, and compiles verified programs back into executable code.We evaluate MAGS on 100 CUDA kernels, 100 terminal scripts, and 20 robotic-arm tasks.

Across all 220 examples, it achieves a 100% success rate in producing programs with non-trivial safety guarantees against frozen specifications.

Independent safety and functional evaluations further show strong performance across all three domains, while revealing failures when the auto-formalized semantics do not fully capture the target behavior.Subjects: Artificial Intelligence (cs.AI); Cryptography and Security (cs.

CR); Software Engineering (cs.SE) Cite as: arXiv:2609.19391 [cs.AI] (or arXiv:2609.19391v1 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2609.

19391 Focus to learn more arXiv-issued DOI via DataCite (pending registration) Submission history From: Albert Wu [view email] [v1] Wed, 16 Sep 2026 20:15:36 UTC (298 KB) Full-text links: Access Paper: View a PDF of the paper titled MAGS: Multi-agent Auto-formalization Guarantees Safety for Agentic Outputs, by Albert Wu and 6 other authorsView PDFHTML (experimental)TeX Source view license Current browse context: cs.

AI < prev | next > new | recent | 2026-09 Change to browse by: cs cs.CR cs.SE References & Citations NASA ADSGoogle Scholar Semantic Scholar export BibTeX citation Loading...BibTeX formatted citation × loading...

Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.

ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv (What is alphaXiv?) Links to Code Toggle CatalyzeX Code Finder for Papers (What is CatalyzeX?) DagsHub Toggle DagsHub (What is DagsHub?

) GotitPub Toggle Gotit.pub (What is GotitPub?) Huggingface Toggle Hugging Face (What is Huggingface?) ScienceCast Toggle ScienceCast (What is ScienceCast?) Demos Demos Replicate Toggle Replicate (What is Replicate?) Spaces Toggle Hugging Face Spaces (What is Spaces?) Spaces Toggle TXYZ.

AI (What is TXYZ.AI?) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower (What are Influence Flowers?) Core recommender toggle CORE Recommender (What is CORE?

) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy.arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community?Learn more about arXivLabs.Which authors of this paper are endorsers?| Disable MathJax (What is MathJax?)