Andras L. Ferenczi, Mariya Bessonov, Allwyn Ponnudurai, Chandrakanth R. Mamillapalli, Krishna K. Maddula, Krishna Lingamneni · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.27272 · cited by 0 works (OpenAlex) · open-access PDF
इस तरह के संवैधानिक एजेंटों को संवैधानिक डेटा लिखने के लिए संवैधानिक एजेंटों की तुलना का परीक्षण करने के लिए एक प्रवासित COBOL अनुप्रयोग लिखना आज एक प्रमुख चुनौती है। हमारे पूर्व लेख, प्राचीन कोड माइग्रेशन के निर्धारित सत्यापन के लिए एजेंटिक विधि, इस तरह के संवैधानिक डेटा लिखने के लिए एक निर्धारित ओरेकल प्रस्तुत करता है, लॉकस्मिथ लूप। हम अब एक उच्च शाखा और पैराग्राफ कवरेज को प्राप्त करने के लिए एक नई विधि की पेशकश करते हैं जेनरेटेड सिंथेटिक एंड-टू-एंड परीक्षण मामलों के माध्यम से, इनपुट-रेप्ले परीक्षण मामलों के प्रमाणन के माध्यम से कोड निष्पादन ट्रैक
Machine translation (Meta M2M100); the English original follows.
Producing synthetic data for comparison testing a migrated COBOL application is a major challenge that agentic migrations face today. Our prior paper, the Agentic Method for Deterministic Validation of Legacy Code Migration, presents a deterministic oracle to facilitate such migrations, the Locksmith Loop. We now propose a novel method for achieving high branch and paragraph coverage through generated synthetic end-to-end test cases, by means of entry-replay test-case certification by observing the code execution trace on a surrogate COBOL program that mocks external interactions via a chronological external-operation tape. We applied our method to a very large COBOL program with 33,429 lines of code to generate 849 synthetic end-to-end test cases covering 2,973/3,806 source branches (78.1%) and 989/1,033 main-AST paragraphs (95.7%). Using the Locksmith Loop's projected-agreement validation, the generated Java code matched the COBOL surrogate on the specified observations across all 849 certified synthetic end-to-end test cases. During the campaign we detected 61 defects and fixed the Java generator accordingly. To test whether the coding agent could silently introduce business logic bugs, we seeded 450 defects into the Java code, such as deleted writes, deleted paragraph calls, and altered rounding, to verify how many of these would be detected by the gating methodology. The gate detected 47.6%, including all deleted writes and paragraph calls in executed code, but was unable to detect the rounding and precision defects.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: COBOL, Computer science, Programming language, Java, Code (set theory), Pointer (user interface)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27272, 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.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange