Newest papers

Conservative Meta-Agent Search: Architecture Adaptation under Non-Stationarity

Ali Alzahrani · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.31436 · cited by 0 works (OpenAlex) · open-access PDF

German

Automatisierte Rate-Überwachung ist ein niedrigeres Ziel-Agent-System-Design wird in der Regel auf statischen Benchmark-Task-Suiten mit unmittelbaren skalaren Belohnungen ausgewertet. Implementierte Systeme konfrontieren sich mit anhaltenden Verschiebungen, verzögerten abhängigen Rückmeldungen, korrelierten Komponentenfehlern und kostspieligeren Architekturänderungen. Wir formalisieren die Meta-Agent-Architektur-Suche als aufeinanderfolgende Eingriffs-Komponenten-Ersatz mit Schaltkosten und harten Risikobeschränkungen. Die Promotion erfordert eine empirisch kalibrierte, varianzbestraft gleichzeitige Suche (CMAS). CMAS holt archivierte Architekturen ab und schlägt typierte Graph-Ed

Machine translation (Meta M2M100); the English original follows.

Abstract

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.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Architecture, Testbed, Component (thermodynamics), Revenue, Regret

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange