Metraipolis › archive › dc_2e90bef8b532

Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change — arXiv:2609.16302

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.16302
License (as archived)
CC0-1.0
Archived
2026-10-15T18:32:48.829Z
SHA-256 of the archived text
bbaf27b968888bdc2648d83d79d5d3dafe56019f351c78763e9b777f36884446
Stable URL of this page
https://metraipolis.com/documento/dc_2e90bef8b532

How to cite

Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change — arXiv:2609.16302 — arXiv (en), https://arxiv.org/abs/2609.16302 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2e90bef8b532 (Metraipolis archive dc_2e90bef8b532, sha256 bbaf27b968888bdc2648d83d79d5d3dafe56019f351c78763e9b777f36884446)
BibTeX
@misc{dc2e90bef8b532,
  title = {Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change — arXiv:2609.16302},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.16302},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2e90bef8b532; sha256 bbaf27b968888bdc2648d83d79d5d3dafe56019f351c78763e9b777f36884446},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.16302. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When a coding agent returns to existing software, it inherits evidence from earlier engineering work: tests, type checks, proofs, static analyses, and traces. Reloading all of it is wasteful, but dropping a piece the change depends on can leave a required property unsupported. Given the properties a change must preserve, its obligations, we ask which least-cost subset of the available evidence re-establishes them, and we call such a subset a task-conditioned assurance envelope. Evidence and the rules that combine it form a typed inference graph; an obligation is met when forward chaining from the selected evidence reaches it, and we validate every selection by that closure rather than by trusting the optimizer. The software-derived graphs in our evaluation come from preserved outcomes of prior AI coding-agent runs; we freeze those artifacts and ask which accumulated evidence should be restored for a later task. Small graphs from Rust, IronBlocks, and Pong outcomes show that the minimum envelope depends on the task, that none may exist when current evidence cannot re-establish a required property, that some properties need several pieces of evidence together, and that expanding the requirements adds evidence rather than replacing it. A prespecified synthetic benchmark of 249 instances characterizes computation: a baseline that discards the 'several pieces together' structure necessarily fails to re-derive them; every completed exact cross-check agreed with the CP-SAT optimizer; and median solve time stayed below 20 ms at 500-evidence graphs, except that graphs with many alternative derivations per target timed out at far smaller sizes, so structure, not raw size, drives difficulty. The contribution is a bounded application of established optimization to selecting assurance context for a software change; discovering the obligations and downstream agent benefit remain open.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-16 in cs.AI).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Programming Languages (cs.PL).
Pagina del lavoro: https://arxiv.org/abs/2609.16302 — 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 2026-10-15T18:03:09.612Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-16?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).