Metraipolis › archive › dc_b5907a1fa724

Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity — arXiv:2610.31436

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.31436
License (as archived)
CC0-1.0
Archived
2026-10-25T21:32:23.658Z
SHA-256 of the archived text
cd7aea9faaaba9738e29e580095cbf1f3d6bc4e79560a61891bc83fbde039cef
Stable URL of this page
https://metraipolis.com/documento/dc_b5907a1fa724

How to cite

Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity — arXiv:2610.31436 — arXiv (en), https://arxiv.org/abs/2610.31436 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b5907a1fa724 (Metraipolis archive dc_b5907a1fa724, sha256 cd7aea9faaaba9738e29e580095cbf1f3d6bc4e79560a61891bc83fbde039cef)
BibTeX
@misc{dcb5907a1fa724,
  title = {Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity — arXiv:2610.31436},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.31436},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b5907a1fa724; sha256 cd7aea9faaaba9738e29e580095cbf1f3d6bc4e79560a61891bc83fbde039cef},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.31436. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Automated agentic-system design is typically evaluated on static task suites with immediate scalar rewards. Deployed systems face persistent shift, delayed dependent feedback, correlated component failures, and costly architecture changes. We formalize meta-agent architecture search as sequential incumbent replacement with switching costs and hard risk constraints and introduce Conservative Meta-Agent Search (CMAS). CMAS retrieves archived architectures and proposes typed graph edits, then scores each against the incumbent by paired shadow replay under common random numbers, with interventional component credit. Promotion requires an empirically calibrated, variance-penalized simultaneous score above a pre-specified margin, and is followed by a simulated canary stage and pre-specified rollback. Since backtests cannot certify meta-level skill, we introduce MetaInvest-Bench, a regime-switching simulator whose specified worker competence makes a surrogate-optimal architecture computable, with leakage-controlled replay, adversarial governance tracks, and five negative controls. Financial streams serve as a risk-sensitive testbed for meta-level generalization; we claim no alpha. Across 96 streams, CMAS cuts normalized mean surrogate dynamic-oracle regret from 0.116 to 0.104 and raises held-out utility from 0.44 to 0.48 over the strongest adaptive baseline; when extra workers add no value, it contracts to near-single-agent teams. Its deployment inference cost is ~6% lower, though its search-inclusive token cost is the highest of the methods compared. The observed per-update false-promotion rate is 3.4% against a nominal 5% target, and 4.8% in a sealed rerun. The calibration is empirical: it concerns an update-level replay statistic on an author-designed benchmark, and guarantees neither full-utility improvement, nor absence of simulated canary-stage harm, nor sequence-level error control.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.31436 — 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 2026-10-25T21:24:47.964Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).