EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Can Edge LLMs Team Up? A Fine-Grained Diagnosis of Multi-Agent Tool Calling

Wenzhi Chen, Zihao Hua, Qichao Lu, Libo Cao, Bo Cheng, Chuanchang Liu, Penghan Song

Electronics · 04.11.2026 · 15 (21) · 5119

DOI: 10.3390/electronics15215119 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Electronics, online erschienen am 04.11.2026. Verfasst von Wenzhi Chen und 6 weiteren Autor:innen. Die Arbeit nennt 34 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Whether edge-scale language models can call tools, and whether teams help, is understudied. We present a fine-grained diagnostic evaluation of tool calling on open-source edge models (0.6B–9B). The single-agent framework measures four dimensions and attributes every run to one of seven failure modes; parameter filling, not tool selection, separates single-agent models. The evaluation extends to multi-agent systems: an orchestrator-workers workflow over 30 MCP tools, a two-layer failure taxonomy of role delegation and worker execution, and a noise-floor protocol of 30 repeats with paired t-tests, exact permutation tests, and bootstrap intervals. Delegation rises steeply with orchestrator scale. Even a Qwen3-0.6B coordinator can delegate: a template-controlled sweep traces its zero delegation to the chat template attached to the model tag rather than to weight precision, and the same weights reach 12.5–22.1% under the template embedded in the model file. Orchestrator-workers teams do not significantly outperform a matched single model or best-of-3, an oracle-aided upper bound rather than a deployable selector, at any scale we tested: delegation overhead consumes the accuracy workers achieve. These findings hold on 4090 GPUs and reproduce on an Ascend 310P NPU. Cross-family runs reproduce the general directional pattern, and the tested orchestrator-workers teams provide no demonstrated advantage over the corresponding single-model baselines under this benchmark and deployment setup.

Förderung

  • National Natural Science Foundation of China

Zitieren

APA

Chen, W., Hua, Z., Lu, Q., Cao, L., Cheng, B., Liu, C., & Song, P. (2026). Can Edge LLMs Team Up? A Fine-Grained Diagnosis of Multi-Agent Tool Calling. Electronics, 15(21), 5119. https://doi.org/10.3390/electronics15215119

Vancouver

Chen W, Hua Z, Lu Q, Cao L, Cheng B, Liu C, et al. Can Edge LLMs Team Up? A Fine-Grained Diagnosis of Multi-Agent Tool Calling. Electronics. 2026;15(21):5119. doi:10.3390/electronics15215119

BibTeX
@article{Chen2026,
  author = {Chen, Wenzhi and Hua, Zihao and Lu, Qichao and Cao, Libo and Cheng, Bo and Liu, Chuanchang and Song, Penghan},
  title = {Can Edge LLMs Team Up? A Fine-Grained Diagnosis of Multi-Agent Tool Calling},
  journal = {Electronics},
  year = {2026},
  volume = {15},
  number = {21},
  pages = {5119},
  doi = {10.3390/electronics15215119}
}
Kostenlos starten →