Metraipolis › archive › dc_920f41872ade
Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering — arXiv:2609.12039
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.12039
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T03:03:07.749Z
- SHA-256 of the archived text
6b20227b0ef62188ad39ed5c835649e5dcf32199ef6457dbb5f061b09664d7ca- Stable URL of this page
https://metraipolis.com/documento/dc_920f41872ade
How to cite
Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering — arXiv:2609.12039 — arXiv (en), https://arxiv.org/abs/2609.12039 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_920f41872ade (Metraipolis archive dc_920f41872ade, sha256 6b20227b0ef62188ad39ed5c835649e5dcf32199ef6457dbb5f061b09664d7ca)
BibTeX
@misc{dc920f41872ade,
title = {Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering — arXiv:2609.12039},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.12039},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_920f41872ade; sha256 6b20227b0ef62188ad39ed5c835649e5dcf32199ef6457dbb5f061b09664d7ca},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.12039. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Software development follows an implementation-verification loop in which developers or agents iteratively revise an implementation until an evaluator, such as a test suite, accepts it. The evaluator checks the implementation against a set of requirements under a model of the deployment environment. Yet even a formal proof that the implementation satisfies the requirements under the model cannot guarantee acceptable behavior after deployment. Requirements only approximate stakeholder intent, and the model only approximates the real deployment environment. We call these together - requirement gap and model gap - the two-gap framework, which unifies the main failure modes of agentic software engineer-ing: reward hacking exploits omissions in the requirements or model, while hallucination widens the gaps by fabricating requirements or environment assumptions. Because neither gap can generally be certified closed in an open, changing world, the goal shifts from closing them to continuously narrowing them. We therefore propose an assurance-revision loop that uses deployment evidence to revise the requirements, model, or evaluator when stakeholders reject the resulting behavior. We then cast assured agentic development as a resource-allocation problem over human judgment, agent capability, and compute. The two principal bottlenecks mirror the two gaps: human judgment for the requirement gap and faithful, costly evaluation for the model gap. Reality remains the final verifier: acceptable behavior under actual deployment conditions is the ultimate test, while predeployment evaluations remain proxies for it. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-14 in cs.AI). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.12039 — 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 2026-10-16T02:51:27.853Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).