Dingxuan Zhang, Yanhui Jiang, Jun Wang, Hefeng Zhou · 2026 · arXiv
DOI: 10.48550/arXiv.2610.31461 · open-access PDF
Keterampilan yang dapat digunakan kembali memungkinkan agen model bahasa besar untuk mengemas prosedur spesifik tugas, affordances alat, dan bimbingan eksekusi menjadi unit modular. Pekerjaan sebelumnya sebagian besar telah mempelajari bagaimana agen mengambil, menyusun, atau mensintesis keterampilan sebelum eksekusi. Dalam agen kode, bagaimanapun, eksekusi menimbulkan masalah kontrol runtime tambahan: tugas yang sama dapat diselesaikan melalui panggilan alat primitif, keterampilan makro, atau eksekusi hibrida yang dimulai dengan makro dan jatuh kembali ke pemulihan mikro-tingkat. Kami memperkenalkan Adaptive Skill Granularity, sebuah kerangka kerja yang memperlakukan keterampilan granularitas sebagai kebijakan tindakan-abstraksi
Machine translation (Meta M2M100); the English original follows.
Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve, compose, or synthesize skills before execution. In coding agents, however, execution poses an additional runtime control problem: the same task may be solved through primitive tool calls, macro skills, or hybrid execution that starts with a macro and falls back to micro-level recovery. We introduce Adaptive Skill Granularity, a framework that treats skill granularity as an action-abstraction polic
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=2610.31461, 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