MAGR-FI: LLM-Based Multi-Agent Game-Theoretic Reasoning Framework for Fire Investigation
Proceedings of the International ISCRAM Conference · 22.05.2026 · 23
DOI: 10.59297/smg7xq63 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the International ISCRAM Conference, online erschienen am 22.05.2026. Verfasst von Chen Tao und 4 weiteren Autor:innen.
Abstract (Originalsprache)
Fire investigation relies heavily on expert experience, rendering it susceptible to cognitive biases and inefficient in processing heterogeneous information. This study proposes an LLM-Based Multi-Agent Game-Theoretic Reasoning Framework for Fire Investigation (MAGR-FI), which integrates the Fire Triangle model from combustion science with the Man-Machine-Environment-Management (MMEM) framework from system safety theory to establish a structured mechanism for hypothesis generation and adversarial validation. The framework employs three specialized agents—Proponent, Skeptic, and Arbiter—engaged in a two-phase dynamic game, enabling interpretable reasoning from unstructured investigative texts to high-confidence causal conclusions. Evaluated on a test set of 1,051 real-world cases, MAGR-FI significantly outperforms baseline large language models, improving average scores from 6.95 to 8.51 and achieving a 120% performance gain on complex cases, thereby providing a reliable, transparent, and auditable intelligent decision-support tool for fire investigation and transforming retrospective causal analysis into actionable knowledge assets for crisis learning and proactive prevention.
Zitieren
APA
Tao, C., Zhang, Y., Huang, L., Dai, J., & Sun, F. (2026). MAGR-FI: LLM-Based Multi-Agent Game-Theoretic Reasoning Framework for Fire Investigation. Proceedings of the International ISCRAM Conference, 23. https://doi.org/10.59297/smg7xq63
Vancouver
Tao C, Zhang Y, Huang L, Dai J, Sun F. MAGR-FI: LLM-Based Multi-Agent Game-Theoretic Reasoning Framework for Fire Investigation. Proceedings of the International ISCRAM Conference. 2026;23. doi:10.59297/smg7xq63
BibTeX
@article{Tao2026,
author = {Tao, Chen and Zhang, Yuhao and Huang, Lida and Dai, Jiakun and Sun, Feihu},
title = {MAGR-FI: LLM-Based Multi-Agent Game-Theoretic Reasoning Framework for Fire Investigation},
journal = {Proceedings of the International ISCRAM Conference},
year = {2026},
volume = {23},
doi = {10.59297/smg7xq63}
}
EUVIMED