Conference paper · 2026 · Open access
An Agentic AI Framework for Severity-Driven Fire Risk Mitigation
IEEE International Conference on AI and Data Analytics (ICAD), 1–8 · Published 1 June 2026 · DOI 10.1109/icad69378.2026.11608618
In brief
“An Agentic AI Framework for Severity-Driven Fire Risk Mitigation” is a 2026 conference paper by Swarnamouli Majumdar and Anjali Awasthi, published in IEEE International Conference on AI and Data Analytics (ICAD). OpenAlex counts 0 citations as of 20 November 2026. It is open access under a CC BY licence: the full text is free to read at IEEE International Conference on AI and Data Analytics (ICAD).
- Citations
- 0
- References
- 12
- Authors
- 2
Abstract
Sustainable public safety systems must increasingly balance risk mitigation effectiveness with constrained resources, operational capacity, and long-term societal impact. In fire risk management, however, success is still commonly evaluated using incident frequency, despite strong empirical evidence that reductions in fire occurrence do not consistently translate into proportional declines in fatalities, injuries, or economic loss. This disconnect undermines the sustainability of prevention strategies by obscuring where limited resources yield the greatest reduction in harm. This paper introduces a severity-aware, agentic AI framework for sustainable fire risk mitigation that explicitly prioritizes outcome-driven impact over incident suppression. Using longitudinal U.S. fire loss data from 2002 to 2011, we empirically demonstrate a weak coupling between fire frequency and fire severity, with a small number of high-impact events accounting for a disproportionate share of societal harm. To operationalize severity as a decision variable, we formalize a Composite Fire Severity Index (CFSI) that integrates fatalities, injuries, and inflation-adjusted economic losses into a unified, policy-controllable metric. Building on this formulation, we propose a Strategic Fire Risk Agent (SFRA) that combines agentic reasoning, reinforcement learning, and constrained optimization to select mitigation strategies under budgetary and operational limits. The framework is further extended through UAV-assisted sensing, which provides adaptive situational awareness to support pre-incident assessment and closed-loop severity reduction. By aligning AI-driven decision-making with consequence-focused risk governance, the proposed framework advances sustainable and resilient public safety systems.
Cite this paper
Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.
APA 7
Majumdar, S., & Awasthi, A. (2026). An Agentic AI Framework for Severity-Driven Fire Risk Mitigation. IEEE International Conference on AI and Data Analytics (ICAD), 1–8. https://doi.org/10.1109/icad69378.2026.11608618
MLA 9
Majumdar, Swarnamouli, and Anjali Awasthi. “An Agentic AI Framework for Severity-Driven Fire Risk Mitigation.” IEEE International Conference on AI and Data Analytics (ICAD), 2026, pp. 1–8. https://doi.org/10.1109/icad69378.2026.11608618.
Chicago
Majumdar, Swarnamouli and Anjali Awasthi. 2026. “An Agentic AI Framework for Severity-Driven Fire Risk Mitigation.” IEEE International Conference on AI and Data Analytics (ICAD): 1–8. https://doi.org/10.1109/icad69378.2026.11608618.
Harvard
Majumdar, S. and Awasthi, A. (2026) ‘An Agentic AI Framework for Severity-Driven Fire Risk Mitigation’, IEEE International Conference on AI and Data Analytics (ICAD), pp. 1–8. doi:10.1109/icad69378.2026.11608618.
IEEE
S. Majumdar and A. Awasthi, “An Agentic AI Framework for Severity-Driven Fire Risk Mitigation,” IEEE International Conference on AI and Data Analytics (ICAD), pp. 1–8, 2026, doi: 10.1109/icad69378.2026.11608618.
BibTeX
@inproceedings{majumdar2026agentic,
title = {{An Agentic AI Framework for Severity-Driven Fire Risk Mitigation}},
author = {Majumdar, Swarnamouli and Awasthi, Anjali},
booktitle = {IEEE International Conference on AI and Data Analytics (ICAD)},
year = {2026},
pages = {1--8},
doi = {10.1109/icad69378.2026.11608618},
url = {https://doi.org/10.1109/icad69378.2026.11608618}
}
Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)
Topic and keywords
Social Sciences › Social Sciences › Safety Research › Safety and Risk Management
- fire risk reduction
- fire severity
- agentic AI
- UAV remote sensing
- situational awareness
- reinforcement learning
- constrained optimization
- risk governance
Work with this paper
Most-cited papers in Social Sciences
- Using thematic analysis in psychologyVirginia Braun, Victoria Clarke · Qualitative Research in Psychology · 2006 · 240,222 citations
- Case Study Research: Design and MethodsRobert K. Yin · 1984 · 81,951 citations
- Three Approaches to Qualitative Content AnalysisHsiu-Fang Hsieh, Sarah Elizabeth Shannon · Qualitative Health Research · 2005 · 49,623 citations
- Qualitative Data Analysis: An Expanded SourcebookMatthew B. Miles, A Michael Huberman · Journal of Environmental Psychology · 1994 · 48,311 citations
- Consolidated criteria for reporting qualitative research (COREQ): a 32-item checklist for interviews and focus groupsAllison Tong, Peter Sainsbury, Jonathan C. Craig · International Journal for Quality in Health Care · 2007 · 45,353 citations
Questions about this paper
How do I cite this paper in APA style?
Majumdar, S., & Awasthi, A. (2026). An Agentic AI Framework for Severity-Driven Fire Risk Mitigation. IEEE International Conference on AI and Data Analytics (ICAD), 1–8. https://doi.org/10.1109/icad69378.2026.11608618
How many times has this paper been cited?
0 times, according to OpenAlex on 20 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.
Is this paper free to read?
Yes. It is open access at IEEE International Conference on AI and Data Analytics (ICAD): sign in and open the full text from this page.
Who wrote this paper?
Swarnamouli Majumdar, Anjali Awasthi.
What is the DOI of this paper?
10.1109/icad69378.2026.11608618, permanently at https://doi.org/10.1109/icad69378.2026.11608618. Sign in and open it from this page.
Bibliographic data from OpenAlex (CC0), last checked 20 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.