Newest papers

VERDICT: Multi-Agent Parallel Modular Verification

Tengjie Lin, Zhongyi Wang, Haokun Li, Jianwei Yin, Mingshuai Chen · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.29147 · cited by 0 works (OpenAlex) · open-access PDF

French

La vérification déductive des contrats est même des échelles de vérification potentielle vers les grands systèmes logiciels par le biais de raisonnements modulaires, où les contrats formels résument le comportement des fonctions individuelles et permettent leur vérification indépendante. Son bouchon central est la synthèse des spécifications complètes: la construction des contrats nécessaires pour la vérification modulaire. Les progrès récents dans les grands modèles linguistiques (LLM) ont permis la synthèse des spécifications automatisées à une échelle sans précédent. Cependant, les approches existantes restent fondamentalement bas-à-bas, ce qui exige que les voies soient vérifiées avant leurs appelants spécifiques. Cette dépendance limite le parallélisme et ne fournit aucun mécan

Machine translation (Meta M2M100); the English original follows.

Abstract

Deductive verification scales to large software systems through modular reasoning, where formal contracts summarize the behavior of individual functions and enable their independent verification. Its central bottleneck is specification synthesis: constructing the contracts required for modular verification. Recent advances in large language models (LLMs) have enabled automated specification synthesis at unprecedented scale. However, existing approaches remain fundamentally bottom-up, requiring callees to be verified before their callers. This dependency limits parallelism and provides no principled mechanism for resolving interprocedural inconsistencies that propagate across call chains. We present VERDICT, a multi-agent framework for parallelizing modular deductive verification of large-scale programs. VERDICT is built on two key principles. First, assumption-based parallel specification synthesis assigns an agent to each function and allows it to proceed immediately using assumed contracts for its callees, enabling verification to proceed in parallel across the program. Second, bidirectional interprocedural conflict reconciliation resolves the inconsistencies introduced by these assumptions: when a synthesized contract contradicts an assumption, agents propagate the necessary revisions both up and down the call graph until the contracts converge. Experimental results on real-world C programs show that VERDICT synthesizes higher-quality specifications than existing approaches while substantially reducing verification time. In particular, VERDICT is the first approach that scales to the complete 20,000-line X.509 parser, ruling out nearly all the potential runtime errors within hours, whereas prior tools like PREGUSS fall far short even after days of execution.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Modular design, Bottleneck, Programming language, Formal verification, Dependency (UML)

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange