Metraipolis › archive › dc_391fa710ac1a

Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning — arXiv:2609.35811

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.35811
License (as archived)
CC0-1.0
Archived
2026-10-07T16:24:43.624Z
SHA-256 of the archived text
6daf32741e03fc9394ecaf0e840a5bcddca1c0d35f8befbdfd2c56deccd0ac09
Stable URL of this page
https://metraipolis.com/documento/dc_391fa710ac1a

How to cite

Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning — arXiv:2609.35811 — arXiv (en), https://arxiv.org/abs/2609.35811 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_391fa710ac1a (Metraipolis archive dc_391fa710ac1a, sha256 6daf32741e03fc9394ecaf0e840a5bcddca1c0d35f8befbdfd2c56deccd0ac09)
BibTeX
@misc{dc391fa710ac1a,
  title = {Lookahead-R: Budget-Aware Tool Retrieval via Execution-Centric Planning — arXiv:2609.35811},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.35811},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_391fa710ac1a; sha256 6daf32741e03fc9394ecaf0e840a5bcddca1c0d35f8befbdfd2c56deccd0ac09},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.35811. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Tool retrieval is a critical bottleneck for LLM-based agents operating over large, heterogeneous API ecosystems. Existing approaches face an inherent trade-off: semantic retrievers are fast but suffer from the semantic-functional gap, while execution-based validation improves precision at the cost of prohibitive latency. We propose Lookahead-R, a planning-based framework that reformulates tool retrieval as a resource-constrained sequential decision-making problem. At its core, Lookahead-R introduces a lightweight execution-aware surrogate world model that jointly predicts tool execution success, latency cost, and semantic utility---without invoking real APIs. This world model drives a cost-sensitive, uncertainty-guided Monte Carlo Tree Search that navigates the tool space under strict budget constraints. Evaluated on the large-scale ToolBench benchmark, Lookahead-R achieves a superior accuracy-efficiency trade-off across all test scenarios. On the most challenging I3 split, it attains an NDCG@5 of 91.40\%, outperforming the state-of-the-art ToolGen (90.16\%) by 1.24\%. Ablation studies confirm that explicit latency modeling is the key discriminative signal for identifying high-quality tools under resource constraints.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-30 in cs.AI).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Software Engineering (cs.SE).
Pagina del lavoro: https://arxiv.org/abs/2609.35811 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-07T15:54:53.712Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-30?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).