Metraipolis › archive › dc_2cd506cb4732

ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback — arXiv:2609.09072

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.09072
License (as archived): CC0-1.0
Archived: 2026-10-16T12:49:29.101Z
SHA-256 of the archived text: 152d16e582ca09d26178a02a04d0865ff8dd13663de9c76d28013614b0b749b3
Stable URL of this page: https://metraipolis.com/documento/dc_2cd506cb4732

How to cite

ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback — arXiv:2609.09072 — arXiv (en), https://arxiv.org/abs/2609.09072 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2cd506cb4732 (Metraipolis archive dc_2cd506cb4732, sha256 152d16e582ca09d26178a02a04d0865ff8dd13663de9c76d28013614b0b749b3)

BibTeX

@misc{dc2cd506cb4732,
  title = {ToolLoop: Closed-Loop Tool-Use Data Synthesis via Decomposed Generation and Dynamic Self-Feedback — arXiv:2609.09072},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.09072},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2cd506cb4732; sha256 152d16e582ca09d26178a02a04d0865ff8dd13663de9c76d28013614b0b749b3},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.09072. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

High-quality tool-use data is critical for training language models to interact effectively with external tools. However, existing synthetic approaches typically follow a generate-then-filter paradigm with static post-hoc verification, often yielding inefficient data with imbalanced feature distributions. We propose ToolLoop, a closed-loop framework that decomposes synthesis into three progressive stages: (1) sampling function name combinations as ground truth; (2) backward derivation of user queries; and (3) forward derivation of tool calls. At each stage, dynamic self-feedback iteratively guides the model toward high-quality generation, realizing a transition from generate-then-filter to generate-verify-refine. On the Berkeley Function Calling Leaderboard (BFCL), a 4B parameter model trained with our 11K synthetic examples achieves 86.40% accuracy in non-reasoning mode, while an Isolate variant that removes BFCL-overlapping candidate functions still reaches 86.07\%. Cross-benchmark evaluation on ACEBench further demonstrates strong generalization, with 72.1% overall accuracy using only 18.3% of baseline training data.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CL).
Categorie arXiv: Computation and Language (cs.CL).
Pagina del lavoro: https://arxiv.org/abs/2609.09072 — 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 2026-10-16T12:30:25.214Z dalla pagina https://arxiv.org/catchup/cs.CL/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).