FM-Agent is the first framework to automate compositional Hoare reasoning for large systems by having LLMs derive natural-language function specs from caller intent and then generate tests that found 522 new bugs in systems up to 143k lines of code.
In Proceedings of the ACM on Programming Languages (OOPSLA)
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.SE 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning
FM-Agent is the first framework to automate compositional Hoare reasoning for large systems by having LLMs derive natural-language function specs from caller intent and then generate tests that found 522 new bugs in systems up to 143k lines of code.