A Bounded Coordination-Support Capability for Multi-Party Settings: Task-State Monitoring in Firefighter Incident Command

David Grünert, Barbara Morgenstern, Florian Peczinka, Dario Holenstein, Roland Brunner, Alexandre de Spindler

Track: Scientific Track

Keywords: Human-AI Collaboration, Multi-Party Communication, Task-State Monitoring, Firefighter Incident Command, Coordination Support

TL;DR: A study of whether an LLM-based incident-command dashboard can track assignment and completion of predefined SOP- and procedure-related tasks from multi-party firefighter radio transcripts without relying on speaker labels or utterance boundaries.

Abstract:

Many collaboration settings require digital support systems for several humans who coordinate through ongoing communication. We study one such application in firefighter incident command: a dashboard that monitors, from radio transcripts, the state of predefined tasks derived from standard operating procedures (SOPs) and related procedures.
Building such a dashboard raises a practical design question: how much transcript structure is actually needed for LLM-based task-state monitoring? More specifically, we examine whether additional transcript structure materially improves monitoring performance, even though it is difficult to obtain reliably from radio communication and increases complexity and latency.
We evaluate this question on source-grounded synthetic firefighter scenarios under transcript conditions that vary speaker identity and utterance boundaries, with incremental inference as the deployment-facing condition and full-transcript inference as an offline reference.
Across repeated runs, incremental monitoring remains strong across all transcript conditions. Differences between transcript structures are small, continuous transcripts remain competitive, and the main weaknesses are unit-related assignment timing and capturing the completion result, which remain broadly similar across conditions.
These results suggest that for this bounded dashboard-support capability, neither speaker identities nor semantically precise utterance boundaries are a primary requirement in the controlled setting studied here.

Submission Number: 47