Paper Detail

Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis

Andrew Szot, Samira Abnar, Omar Attia, Abbas Kazerouni, Michael Kirchhof, Cheng-Yu Hsieh, Raviteja Vemulapalli, Alexander Toshev

arxiv Score 14.3

Published 2026-10-27 · First seen 2026-10-28

General AI

Abstract

We explore how to build performant large language model (LLM) tool-use agents that complete complex, multi-step tasks. Specifically, we study how data composition in synthetically generated tool-use environments affects the training of such agents. To do so, we propose the SynthAPI pipeline, which explicitly controls the diversity of generated environments along the axes of tools, tasks, and the databases on which the tools operate. By systematically varying SynthAPI's generation controls in 458,752 tasks across 849 trained models of four different sizes, we derive a scaling law that predicts downstream tool-use agent generalization based on the scale and composition of the synthesized environments. These predictable relationships reveal several lessons for scaling tool-use agent data. As data budgets grow, scaling tool and database diversity becomes more effective than increasing the number of tasks, and increasing data complexity yields larger gains. Scaling according to these findings yields agents that outperform models trained on data from prior work in large-scale tool-use agent and synthetic environment generation across four evaluation benchmarks.

Workflow Status

Review status
pending
Role
unreviewed
Read priority
now
Vote
Not set.
Saved
no
Collections
Not filed yet.
Next action
Not filled yet.

Reading Brief

No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.

Why It Surfaced

No ranking explanation is available yet.

Tags

No tags.

BibTeX

@article{szot2026scaling,
  title = {Scaling Laws for Tool-Use Agents via Controllable Environment Synthesis},
  author = {Andrew Szot and Samira Abnar and Omar Attia and Abbas Kazerouni and Michael Kirchhof and Cheng-Yu Hsieh and Raviteja Vemulapalli and Alexander Toshev},
  year = {2026},
  abstract = {We explore how to build performant large language model (LLM) tool-use agents that complete complex, multi-step tasks. Specifically, we study how data composition in synthetically generated tool-use environments affects the training of such agents. To do so, we propose the SynthAPI pipeline, which explicitly controls the diversity of generated environments along the axes of tools, tasks, and the databases on which the tools operate. By systematically varying SynthAPI's generation controls in 458},
  url = {https://arxiv.org/abs/2610.37648},
  keywords = {cs.LG},
  eprint = {2610.37648},
  archiveprefix = {arXiv},
}

Metadata

{}