Amit Lisha, Reut Tsarfaty · 2026 · arXiv
DOI: 10.48550/arXiv.2610.28311 · open-access PDF
自然言語の指示はしばしば高レベルの抽象に依存し、例えばエージェントに「ピラミッドでブロックを積み重ねる」ことを要求するなど、抽象的な指示を解釈するには、モデルがスピーカーが意図する抽象を識別し、それをインスタンスする多くの具体的なアクションに解読する必要があります。言語モデルはここで苦労します:以前の研究は、指示の抽象レベルが上昇するにつれてパフォーマンスが低下することを示しています。
Machine translation (Meta M2M100); the English original follows.
Natural-language instructions often rely on high-level abstractions, such as asking an agent to ``stack blocks in a pyramid.'' Interpreting abstract instructions requires models to both identify the abstraction intended by the speaker, and unroll it into the many concrete actions that instantiate it. Language models struggle here: prior work has shown that performance degrades as the level of abstraction in the instruction rises. To bridge the gap between natural language abstraction and concrete actions, we propose to borrow from coding environments the notion of a {\em domain-specific langua
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=2610.28311, 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