EUVIMEDEUVIMED entdecken
Crossref

S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning

Jiangwen Dong, Zehui Lin, Wanyu Lin, Mingjin Zhang

Proceedings of the AAAI Conference on Artificial Intelligence · 14.03.2026 · 40 (35) · 29394-29402

DOI: 10.1609/aaai.v40i35.40180 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 14.03.2026. Verfasst von Jiangwen Dong und 3 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Large Language Models (LLMs) have achieved impressive performance in complex reasoning problems. Their effectiveness highly depends on the specific nature of the task, especially the required domain knowledge. Existing approaches, such as mixture-of-experts, typically operate at the task level; they are too coarse to effectively solve the heterogeneous problems involving multiple subjects. This work proposes a novel framework that performs fine-grained analysis at subject level equipped with a designated multi-agent collaboration strategy for addressing heterogeneous problem reasoning. Specifically, given an input query, we first employ a Graph Neural Network to identify the relevant subjects and infer their interdependencies to generate an Subject-based Directed Acyclic Graph (S-DAG), where nodes represent subjects and edges encode information flow. Then we profile the LLM models by assigning each model a subject-specific expertise score, and select the top-performing one for matching corresponding subject of the S-DAG. Such subject-model matching enables graph-structured multi-agent collaboration where information flows from the starting model to the ending model over S-DAG. We curate and release multi-subject subsets of standard benchmarks (MMLU-Pro, GPQA, MedMCQA) to better reflect complex, real-world reasoning tasks. Extensive experiments show that our approach significantly outperforms existing task-level model selection and multi-agent collaboration baselines in accuracy and efficiency. These results highlight the effectiveness of subject-aware reasoning and structured collaboration in addressing complex and multi-subject problems.

Zitieren

APA

Dong, J., Lin, Z., Lin, W., & Zhang, M. (2026). S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence, 40(35), 29394-29402. https://doi.org/10.1609/aaai.v40i35.40180

Vancouver

Dong J, Lin Z, Lin W, Zhang M. S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning. Proceedings of the AAAI Conference on Artificial Intelligence. 2026;40(35):29394-29402. doi:10.1609/aaai.v40i35.40180

BibTeX
@article{Dong2026,
  author = {Dong, Jiangwen and Lin, Zehui and Lin, Wanyu and Zhang, Mingjin},
  title = {S-DAG: A Subject-Based Directed Acyclic Graph for Multi-Agent Heterogeneous Reasoning},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2026},
  volume = {40},
  number = {35},
  pages = {29394--29402},
  doi = {10.1609/aaai.v40i35.40180}
}
Kostenlos starten →