EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Autonomous Agents Based on Large Language Models: Reasoning Strategies and Multi-Agent Interaction

Zhengyuan Wang, Yuyao Wang, Yixin Deng

Transactions on Computing Science · 2026

DOI: 10.63808/tcs.v2i2.519 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Transactions on Computing Science, 2026. Verfasst von Zhengyuan Wang und 2 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Language-model agents acquire capability along two routes that published work almost always varies together, one enlarging the computation a single agent performs and the other enlarging the number of agents and the channels along which they pass partial results, which leaves the contribution of each route indistinguishable. This paper separates an agent system into a reasoning operator and an interaction topology, holding the number of agents fixed at three across all multi-agent topologies, together with the number of rounds, the message cap, the prompt skeleton, and the memory settings for all combinations, and evaluates a full factorial design of four reasoning levels and four topologies on three public test sets totalling 484 instances under five random seeds, giving 38,720 task executions. Comparisons are paired at the instance level, and effects are estimated from logistic mixed-effects models fitted to each test set separately. The reasoning factor spans 18.0 points on the static suite whereas the topology factor spans 7.8 points on the interactive one, a reversal indicating that the two mechanisms act on different failure modes. The topology span is taken across all four topology levels and therefore includes the step from one agent to three, against a structure-only span of 2.8 points among the multi-agent topologies. The two factors also depart from additivity in a localised manner. A mechanism-motivated single-degree-of-freedom contrast on the only cell in which both factors contribute a corrective pass is significant at p = 0.001 on the static suite, whereas the omnibus nine-degree-of-freedom interaction test is not (p = 0.094), and in that cell the observed 50.0 percent lies 5.8 points below the additive expectation. After tokens are counted, seven of the sixteen configurations remain undominated on the static suite and five on the operating-system suite, and returns saturate at 12,400 tokens per instance on the static suite under the present design.

Zitieren

APA

Wang, Z., Wang, Y., & Deng, Y. (2026). Autonomous Agents Based on Large Language Models: Reasoning Strategies and Multi-Agent Interaction. Transactions on Computing Science. https://doi.org/10.63808/tcs.v2i2.519

Vancouver

Wang Z, Wang Y, Deng Y. Autonomous Agents Based on Large Language Models: Reasoning Strategies and Multi-Agent Interaction. Transactions on Computing Science. 2026. doi:10.63808/tcs.v2i2.519

BibTeX
@article{Wang2026,
  author = {Wang, Zhengyuan and Wang, Yuyao and Deng, Yixin},
  title = {Autonomous Agents Based on Large Language Models: Reasoning Strategies and Multi-Agent Interaction},
  journal = {Transactions on Computing Science},
  year = {2026},
  doi = {10.63808/tcs.v2i2.519}
}
Kostenlos starten →