ResQConnect: An AI-Powered Multi-Agentic Platform for Human-Centered and Resilient Disaster Response

ResQConnect: многоагентная платформа на основе искусственного интеллекта для человекоориентированного и устойчивого реагирования на чрезвычайные ситуации
Biswajeet Pradhan, Dulani Meedeniya, Savinu Aththanayake, Chemini Mallikarachchi, Janeesha Wickramasinghe, Sajeev Kugarajah
2026-01-19

adaptive event-triggered routingagentic retrieval-augmented generationmulti-agent disaster responsemultimodal disaster managementoffline language model deployment
Effective disaster management is critical for safeguarding lives, infrastructure and economies in an era of escalating natural hazards like floods and landslides. Despite advanced early-warning systems and coordination frameworks, a persistent “last-mile” challenge undermines response effectiveness: transforming fragmented and unstructured multimodal data into timely and accountable field actions. This paper introduces ResQConnect, a human-centered, AI-powered multimodal multi-agent platform that bridges this gap by directly linking incident intake to coordinated disaster response operations in hazard-prone regions. ResQConnect integrates three key components. It uses an agentic Retrieval-Augmented Generation (RAG) workflow in which specialized language-model agents extract metadata, refine queries, check contextual adequacy and generate actionable task plans using a curated, hazard-specific knowledge base. The contribution lies in structuring the RAG for correctness, safety and procedural grounding in high-risk settings. The platform introduces an Adaptive Event-Triggered (AET) multi-commodity routing algorithm that decides when to re-optimize routes, balancing responsiveness, computational cost and route stability under dynamic disaster conditions. Finally, ResQConnect deploys a compressed, domain-specific language model on mobile devices to provide policy-aligned guidance when cloud connectivity is limited or unavailable. Across realistic flood and landslide scenarios, ResQConnect improved overall task-quality scores from 61.4 to 82.9 (+21.5 points) over a standard RAG baseline, reduced solver calls by up to 85% compared to continuous re-optimization while remaining within 7–12% of optimal response time, and delivered fully offline mobile guidance with sub-500 ms response latency and 54 tokens/s throughput on commodity smartphones. Overall, ResQConnect demonstrates a practical and resilient approach to AI-augmented disaster response. From a sustainability perspective, the proposed system contributes to Sustainable Development Goal (SDG) 11 by improving the speed and coordination of disaster response. It also supports SDG 13 by strengthening adaptation and readiness for climate-driven hazards. ResQConnect is validated using real-world flood and landslide disaster datasets, ensuring realistic incidents, constraints and operational conditions.
1
A compressed domain-specific model enabled fully offline mobile guidance with sub-500 ms latency and 54 tokens per second on commodity smartphones.
2
Across realistic flood and landslide scenarios, ResQConnect increased task-quality scores from 61.4 to 82.9, improving 21.5 points over standard RAG.
3
Its agentic RAG workflow uses specialized agents and hazard-specific knowledge to improve correctness, safety, contextual adequacy, and procedural grounding.
4
ResQConnect links multimodal incident intake to coordinated disaster-response actions through a human-centered, multi-agent AI platform.
5
The adaptive event-triggered routing algorithm reduced solver calls by up to 85% versus continuous re-optimization while staying within 7–12% of optimal response time.

ResQConnect, an AI-powered multimodal multi-agent platform for disaster response in flood- and landslide-prone regions

Human-centered and resilient disaster-response operations, including multimodal incident-to-action coordination, adaptive routing, and offline policy-aligned guidance under dynamic and connectivity-constrained conditions

Publication Details
Publication Date
2026-01-19
Journal
Publisher
ISSN
Cited by
8
Access Type
Author Information
Authors
Biswajeet Pradhan
Dulani Meedeniya
Savinu Aththanayake
Chemini Mallikarachchi
Janeesha Wickramasinghe
Sajeev Kugarajah
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%