Qian Xie, Wenyue Hua, Yueli He, Sripad Karne, Armaan Agrawal, Nikos Pagonas, Eugene Wu, Kostis Kaffes, Tianyi Peng, Nairen Cao · 2026 · arXiv (Cornell University)
DOI: 10.48550/arxiv.2610.26676 · cited by 0 works (OpenAlex) · open-access PDF
LLM агентские рабочие процессы все чаще используют различные модели для специализированных ролей. Пользователи могут предпочесть различные компромиссы между качеством задания и затратами на развертывание, иногда также учитывая задержку. Найти хорошие задания влечет за собой отдельные затраты на поиск от оценки нескольких кандидатов. Мы вводим развернутые за счет затрат Gittins (CC-Gittins), многоцелевое расширение одноцелевого целеустремленного поиска Gittins по рекомендации Pareto. Он использует связь между оценкой и затратами на развертывание: задания, которые стоят больше на развертывание, также стоят больше на оценку. Поиск чередуется между поиском более высокого качества и более низких затрат на развертывание, повторно используя каждую оценку,
Machine translation (Meta M2M100); the English original follows.
LLM agentic workflows increasingly employ different models for specialized roles. Users may prefer different trade-offs between task quality and deployment cost, sometimes also considering latency. Finding good assignments incurs a separate search cost from evaluating multiple candidates. We introduce Cost-Coupled Gittins (CC-Gittins), a multi-objective extension of single-objective cost-aware Gittins search for Pareto recommendation. It exploits the coupling between evaluation and deployment costs: assignments that cost more to deploy also cost more to evaluate. The search alternates between seeking higher quality and lower deployment cost, reusing each evaluation to inform both searches. After each batch, CC-Gittins recommends assignments that are nondominated under uncertainty-adjusted estimates of quality and deployment cost. We evaluate CC-Gittins on eight quality--cost matrices from workflows with two to five roles and up to 1,681 candidate assignments. We also evaluate the method with latency as a third objective. Across the eight benchmarks, CC-Gittins recovers a substantial fraction of the true Pareto frontier at roughly 10% of the exhaustive-evaluation cost, and recovers most of the frontier with few false positives by 30%.
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Workflow, Software deployment, Computer science, Pareto principle, Exploit, Task (project management)
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.26676, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange