mlsanityData to 14 Oct 2026

Enhancing Operational Safety via Agentic Dialogue Hazard Identification Analysis

arXiv 2606.03812 ↗First posted 2 Jun 2026cs.AIcited by 0

On the map: LLM agents and tool use → Agent threats, guardrails and governance

Abstract (arXiv)

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 algorithm-based agentic interaction optimization. We evaluate all configurations against a curated golden dataset using standard classification metrics (accuracy, precision, recall, F1) and novel dialogue metrics. This work advances the intersection of dialogue systems, multi-agent reasoning, and AI safety, providing an empirical evidence for dialogue-driven hazard analysis.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use. Builds on 15 of its 44 references that are in the map. First posted on arXiv 2 Jun 2026.

Builds on

15 of 44 references.

References · 15

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2022Large Language Models are Zero-Shot Reasonerscited by 4,374
  4. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,568
  5. 2019Fine-Tuning Language Models from Human Preferencescited by 2,150
  6. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,784
  7. 2018Know What You Don't Know: Unanswerable Questions for SQuADcited by 1,554
  8. 2023Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debatecited by 1,011
  9. 2023Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMscited by 974
  10. 2023Large Language Models Are Not Robust Multiple Choice Selectorscited by 486
  11. 2016Deep Reinforcement Learning for Dialogue Generationcited by 288
  12. 2024EvoAgent: Towards Automatic Multi-Agent Generation via Evolutionary Algorithmscited by 113
3 more
  1. 2021Auto-FuzzyJoin: Auto-Program Fuzzy Similarity Joins Without Labeled Examplescited by 15
  2. 2024GenBFA: An Evolutionary Optimization Approach to Bit-Flip Attacks on LLMscited by 10
  3. 2021A surrogate loss function for optimization of Fβ score in binary classification with imbalanced datacited by 5

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
  2. 2025AgenticEval: Toward Agentic and Self-Evolving Safety Evaluation of Large Language Models
  3. 2024R-Judge: Benchmarking Safety Risk Awareness for LLM Agents
  4. 2026Discovering Agentic Safety Specifications from 1-Bit Danger Signals
  5. 2026PASTABench: Proactive Assessment of Sequential Trajectories for Agent Safety
  6. 2026Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
  7. 2026Risky-Bench: Probing Agentic Safety Risks under Real-World Deployment
  8. 2026SafePro: Evaluating the Safety of Professional-Level AI Agents