Metraipolis › archive › dc_14ff8d98db69
Schwarz: Solver-Aware Agentic Program Verification — arXiv:2608.30803
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.30803
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T08:59:41.391Z
- SHA-256 of the archived text
ec04c8b650091ea23c77e64a74919c1eac0955ace1230d7e1f1f7f5a8c96a415- Stable URL of this page
https://metraipolis.com/documento/dc_14ff8d98db69
How to cite
Schwarz: Solver-Aware Agentic Program Verification — arXiv:2608.30803 — arXiv (en), https://arxiv.org/abs/2608.30803 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_14ff8d98db69 (Metraipolis archive dc_14ff8d98db69, sha256 ec04c8b650091ea23c77e64a74919c1eac0955ace1230d7e1f1f7f5a8c96a415)
BibTeX
@misc{dc14ff8d98db69,
title = {Schwarz: Solver-Aware Agentic Program Verification — arXiv:2608.30803},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.30803},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_14ff8d98db69; sha256 ec04c8b650091ea23c77e64a74919c1eac0955ace1230d7e1f1f7f5a8c96a415},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.30803. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic verification systems can often generate source-level specifications that look plausible, but plausibility is not enough: the verifier must still turn those specifications into SMT obligations that the solver can prove. When this step fails, current LLM-driven loops usually expose only a coarse verifier error, timeout, or unknown solver result. The model cannot tell whether the specification is wrong, a helper lemma is missing, the proof context contains irrelevant facts, or the obligation needs a different theory view. This paper presents Schwarz, an agentic verification harness that makes SMT-backed proof failure local, checkable, and repairable. Schwarz turns failed verification into obligation-local repair tasks: program-point snapshots expose checked facts at a boundary, local lemmas let the agent propose missing proof steps, and theory-aware solver policies guide the agent toward solver-friendly formulations for numeric, quantified, memory, and floating-point obligations. We implement Schwarz for C and Rust/Verus and evaluate it on 1,475 tasks. On 475 benchmarks from recent agentic verification tools, Schwarz solves 95.2% of the tasks. On 1,000 tasks from the SV-COMP 2026 ReachSafety track, averaging 1,427 LOC, Schwarz solves 91.5% of the tasks, compared with 60.1% for CPAchecker. Ablations and comparison with a pure-agent baseline show that solver-aware repair is effective and scalable. Tema degli esploratori: calcolo e infrastrutture (retro-catalogo arXiv: annunci del 2026-09-01 in cs.SE). Categorie arXiv: Logic in Computer Science (cs.LO) ; Software Engineering (cs.SE). Pagina del lavoro: https://arxiv.org/abs/2608.30803 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T08:37:02.104Z dalla pagina https://arxiv.org/catchup/cs.SE/2026-09-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).