Tom A. Lamb, Adam Golinski, Eleonora Gualdoni, Sinead Williamson, Michael Kirchhof · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28409 · open-access PDF
대형 언어 모델 에이전트는 종종 추론 예산을 받으며 그 안에서 성공을 극대화하도록 요청받습니다. 다중 회전 에이전트는 많은 환경 상호 작용을 통해이 예산을 할당해야합니다. 외부 핸들러는 예산을 강요 할 수 있지만 에이전트 자체가 언제 그리고 얼마를 지출할 수 있는지 여부는 명확하지 않습니다. 우리는 에이전트가 역동적으로 지정된 예산을 통해이 할당을 배울 수 있는지, 어떤 보상이이이 행동을 가장 잘 가르치는지 여부를 묻습니다.
Machine translation (Meta M2M100); the English original follows.
Large language model agents are often given an inference budget and asked to maximise success within it. A multi-turn agent has to allocate this budget across many environment interactions. An external harness can enforce the budget, but it remains unclear whether the agent itself can learn when and how much to spend. We ask whether agents can learn this allocation across dynamically specified budgets and which rewards best teach this behaviour. We adapt existing length penalties to budget constraints spanning multiple resource types, introduce new reward formulations, and compare eleven objec
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=2610.28409, 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