Metraipolis › archive › dc_aebe2e734419

AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models — arXiv:2608.23078

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.23078
License (as archived)
CC0-1.0
Archived
2026-10-18T07:41:50.125Z
SHA-256 of the archived text
aeb07d534a019afed8a5cbfd4d78e6721fc0ad5ec4bd97a816c4117fc5c471be
Stable URL of this page
https://metraipolis.com/documento/dc_aebe2e734419

How to cite

AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models — arXiv:2608.23078 — arXiv (en), https://arxiv.org/abs/2608.23078 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_aebe2e734419 (Metraipolis archive dc_aebe2e734419, sha256 aeb07d534a019afed8a5cbfd4d78e6721fc0ad5ec4bd97a816c4117fc5c471be)
BibTeX
@misc{dcaebe2e734419,
  title = {AgentWeave: Routing Before Reasoning for Efficient Function Calling in Tool-Rich Language Models — arXiv:2608.23078},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23078},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_aebe2e734419; sha256 aeb07d534a019afed8a5cbfd4d78e6721fc0ad5ec4bd97a816c4117fc5c471be},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23078. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Large language models increasingly operate over large collections of tools, functions, APIs, and specialized agents. As the candidate action space grows, a function-calling model must process more schemas, consume more prompt tokens, and distinguish among increasingly similar or irrelevant alternatives. We study a complementary systems strategy: reduce the candidate set before language-model inference while leaving the downstream model unchanged. We introduce AgentWeave, a deterministic pre-inference routing layer that constructs a bounded model-visible action space using eligibility, requirement, capability, and routing signals. We evaluate AgentWeave with a frozen BFCL-derived routing-pressure protocol using the public MadeAgents/Hammer2.1-1.5b model. On 48 fresh BFCL V4 multiple-function tasks, AgentWeave achieves 6/48 (12.5%) native BFCL successes, whereas all-tools, deterministic random top-8, and semantic top-8 baselines each achieve 0/48. The paired success difference is +12.5 percentage points with a 10,000-resample paired bootstrap 95% confidence interval of +4.17 to +22.92 points and exact McNemar p=0.03125. Relative to all-tools exposure, AgentWeave presents 70.18% fewer tools, uses 61.70% fewer input tokens, and exhibits 50.95% lower mean local-model latency. The result is deliberately narrow: this is a BFCL-derived routing-pressure study rather than an official full BFCL leaderboard score, and absolute task success remains low. The evidence nevertheless shows that candidate-space construction can materially affect a fixed model's function-calling behavior and motivates evaluating routing as a distinct stage before model reasoning.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2608.23078 — 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 2026-10-18T07:37:52.766Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).