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

Hindi

डिडक्टिव अनुबंध सत्यापन भी बड़े सॉफ्टवेयर प्रणालियों को मॉड्यूलर तर्क के माध्यम से संदर्भित करता है, जहां औपचारिक अनुबंध व्यक्तिगत कार्यों के व्यवहार को संक्षेपित करते हैं और उनकी स्वतंत्र सत्यापन की अनुमति देते हैं। इसकी केंद्रीय बोतललनक विनिर्देश संश्लेषण है: मॉड्यूलर सत्यापन के लिए आवश्यक अनुबंधों का निर्माण। बड़े भाषा मॉडल (एलएलएमएस) में हाल के प्रगति ने स्वचालित विनिर्देश संश्लेषण को अनगिनत पैमाने पर सक्षम किया है. हालांकि, मौजूदा दृष्टिकोण मूल रूप से नीचे से ऊपर रहते हैं, जबकि उनके कॉलर से पहले सत्यापन की आवश्यकता होती है। यह निर्भरता पारंपरिकता को सीमित करती है और

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)

Is this paper real? This page was built from OpenAlex and arXiv records, not generated. Software can verify any reference in one call: GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.29147, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txt

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