Ivan Ilin, Peter Richtárik · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28286 · open-access PDF
대형 언어 모델 (LLM) 에이전트 팀은 점점 더 복잡한 작업에 적용되지만, 그들의 협업 프로토콜은 대부분 실험적으로 설계되며 협력 문제 해결을 블록 최적화로 공식화합니다 : 각 에이전트는 공유 솔루션의 한 부분을 개선하고, 지역 목표에 따라 변경이 다른 부분에 어떻게 영향을 미치는지에 대한 수정을 제공합니다. 코디네이터는 글로벌 목표에 대한 각 제안을 검사하고 서로 간섭하지 않는 제안을 합병합니다.
Machine translation (Meta M2M100); the English original follows.
Teams of large language model (LLM) agents are increasingly applied to complex tasks, but their collaboration protocols are mostly designed empirically, without convergence guarantees. We formalize collaborative problem solving as block optimization: each agent improves one part of a shared solution, guided by its local objective plus a correction for how its changes affect the other parts. A coordinator checks every proposal against the global objective and merges proposals that do not interfere with each other. We prove linear convergence up to an error floor that vanishes when the correctio
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.28286, 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