Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

Sanjay Das, Ran Elgedawy, Ethan Seefried, Ryan Burchfield, Tirthankar Ghosal


Abstract
Operational safety in high-stakes domains such as industrial process control, autonomous, and safety-critical systems demand reliable hazard identification. While large language models (LLMs) have shown promise in automating safety analysis tasks, single-turn, monolithic inference is brittle: it lacks the self-correction, deliberation, and contextual refinement that safety engineers apply iteratively. In this paper, we introduce HAZDIAL, a framework that investigates whether structured agentic dialogue (multi-agent, multi-turn interactions) improves the quality of NLP-based hazard identification over single-pass baselines. We systematically compare two dialogue modalities: adversarial debate and constructive discussion, and propose an genetic algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and a novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing empirical evidence for dialogue-driven hazard analysis.
Anthology ID:
2026.sigdial-1.53
Volume:
Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue
Month:
August
Year:
2026
Address:
Atlanta, Georgia, USA
Editors:
Jinho D. Choi, Yun-Nung Chen, Kotaro Funakoshi, Ali Emami
Venue:
SIGDIAL
SIG:
SIGDIAL
Publisher:
Association for Computational Linguistics
Note:
Pages:
757–772
Language:
URL:
https://aclanthology.org/2026.sigdial-1.53/
DOI:
Bibkey:
Cite (ACL):
Sanjay Das, Ran Elgedawy, Ethan Seefried, Ryan Burchfield, and Tirthankar Ghosal. 2026. Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis. In Proceedings of the 27th Annual Meeting of the Special Interest Group on Discourse and Dialogue, pages 757–772, Atlanta, Georgia, USA. Association for Computational Linguistics.
Cite (Informal):
Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis (Das et al., SIGDIAL 2026)
Copy Citation:
PDF:
https://aclanthology.org/2026.sigdial-1.53.pdf