Metraipolis › archive › dc_e44a433b0176

Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search — arXiv:2610.04829

Source
arXiv
Original
https://arxiv.org/abs/2610.04829
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:01.587Z
SHA-256 of the archived text
eb542c727b394b49adb926e20d647b9d5c9fbe28ec8d307c20d7919e838f71de
Stable URL of this page
https://metraipolis.com/documento/dc_e44a433b0176

How to cite

Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search — arXiv:2610.04829 — arXiv, https://arxiv.org/abs/2610.04829 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e44a433b0176 (Metraipolis archive dc_e44a433b0176, sha256 eb542c727b394b49adb926e20d647b9d5c9fbe28ec8d307c20d7919e838f71de)
BibTeX
@misc{dce44a433b0176,
  title = {Viva La Vida: Verification and Accumulation Failures in Multi-Agent Proof Search — arXiv:2610.04829},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04829},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e44a433b0176; sha256 eb542c727b394b49adb926e20d647b9d5c9fbe28ec8d307c20d7919e838f71de},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04829. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

When an agentic prover works on an open problem, there is no proof assistant to fall back on: its verifier and lemma library are ultimately language models judging model outputs. We instrumented such a system end to end and analyzed $51{,}754$ traced observations across three full runs ($186$ hours, \$$5{,}694$). We find three connected failure modes. First, the three-model verifier requires unanimity and treats parse or API failure as non-approval; in $10$ of $12$ verification events, one member returned no parseable output or an API error, making acceptance arithmetically impossible without surfacing an error. Second, when the ensemble did function, one verifier approved $3$ attempts that GPT rejected, each claiming to resolve the open problem; a single-verifier design would therefore have announced a solution three times. Third, because nothing could be approved, every review was a refutation, yet the lemma extractor mines reviews as well as proofs: $24$ of $93$ lemmas ($26\%$) were extracted from rejected arguments with their refutational context removed. Taken together, these findings show that without external verification, supervision is itself a critical trust boundary: systems must distinguish abstention from rejection, preserve useful disagreement, and preserve the provenance and polarity of information before it becomes future context.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.04829 — 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 2026-10-06T05:23:50.233Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).