Metraipolis › archive › dc_c2b87ef8de6d

Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering — arXiv:2610.39468

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39468
License (as archived)
CC0-1.0
Archived
2026-10-31T06:06:49.707Z
SHA-256 of the archived text
137aeeb12c777ee8365c5d6824b8527b909d731655cbae2163982b85d3a49d05
Stable URL of this page
https://metraipolis.com/documento/dc_c2b87ef8de6d

How to cite

Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering — arXiv:2610.39468 — arXiv (en), https://arxiv.org/abs/2610.39468 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c2b87ef8de6d (Metraipolis archive dc_c2b87ef8de6d, sha256 137aeeb12c777ee8365c5d6824b8527b909d731655cbae2163982b85d3a49d05)
BibTeX
@misc{dcc2b87ef8de6d,
  title = {Soei: Structured Observability of Evidence and Intent for Multi-Agent AI Software Engineering — arXiv:2610.39468},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39468},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c2b87ef8de6d; sha256 137aeeb12c777ee8365c5d6824b8527b909d731655cbae2163982b85d3a49d05},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39468. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

AI coding agents now do long, multi-step and multi-session software work with little supervision. When a developer comes back to that work, the useful question is not what the model said but what was actually done, by whom, and whether it is finished. We study this in three parts. First, we verify Agenttrail, an open-source local observability tool for coding agents, against its source at commit e4ba2da: nine documented constants and mechanisms hold at file-and-line level, two event pipelines are never unified, and its Map service has an unauthenticated local mutation surface. Second, we run a prototype of our system on 45 real coding-agent sessions (102,233 records, 20,577 tool executions, 2,336 human-to-agent episodes). With a blind-audited classifier (precision 83.3% and 96.7%) we estimate that 23.4% (95% CI 17.1 to 35.7) of code-editing episodes end with no independent check after the last edit, and that 57.8% of to-dos the agent marked complete after editing had no proof in between. A 10-minute timing heuristic for session hand-offs recovers 6 of the 24 session pairs that content lineage links. 42% of sessions run longer than 24 hours, 48.1% of transcript bytes lie past a 2 MiB replay bound, and 1,326 records in 16 sessions contain credential-like strings. Third, we propose Soei (Structured Observability of Evidence and Intent): an acknowledgement-aware event schema, a hash-chained local ledger, a W3C PROV-aligned graph, calibrated inference for attribution and lineage, and a verification layer that keeps a claim of completion apart from proof. On the same corpus the ledger is 20% of raw size, holds no content or credentials, verifies at about 126k events/s, detects tampering and replays deterministically. We position the work against concurrent 2026 proposals and define autonomy levels with evidence gates and harness metrics baselined on our data.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.39468 — 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 2026-10-31T06:06:38.431Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).