mlsanityData to 14 Oct 2026

Entropy-Constrained Strategy Optimization in Urban Floods: A Multi-Agent Framework with LLM and Knowledge Graph Integration

arXiv 2508.14654 ↗First posted 20 Aug 2025cs.AIcited by 0

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

In recent years, the increasing frequency of extreme urban rainfall events has posed significant challenges to emergency scheduling systems. Urban flooding often leads to severe traffic congestion and service disruptions, threatening public safety and mobility. However, effective decision making remains hindered by three key challenges: (1) managing trade-offs among competing goals (e.g., traffic flow, task completion, and risk mitigation) requires dynamic, context-aware strategies; (2) rapidly evolving environmental conditions render static rules inadequate; and (3) LLM-generated strategies frequently suffer from semantic instability and execution inconsistency. Existing methods fail to align perception, global optimization, and multi-agent coordination within a unified framework. To tackle these challenges, we introduce H-J, a hierarchical multi-agent framework that integrates knowledge-guided prompting, entropy-constrained generation, and feedback-driven optimization. The framework establishes a closed-loop pipeline spanning from multi-source perception to strategic execution and continuous refinement. We evaluate H-J on real-world urban topology and rainfall data under three representative conditions: extreme rainfall, intermittent bursts, and daily light rain. Experiments show that H-J outperforms rule-based and reinforcement-learning baselines in traffic smoothness, task success rate, and system robustness. These findings highlight the promise of uncertainty-aware, knowledge-constrained LLM-based approaches for enhancing resilience in urban flood response.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 15 of its 39 references that are in the map. First posted on arXiv 20 Aug 2025.

Builds on

15 of 39 references.

References · 15

  1. 2024Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputscited by 150
  2. 2023Predicting Question-Answering Performance of Large Language Models through Semantic Consistencycited by 28
  3. 2025SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Modelscited by 19
  4. 2017Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Networkcited by 16
  5. 2022SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Controlcited by 15
  6. 2025HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinkingcited by 14
  7. 2024KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Modelscited by 12
  8. 2025Improving Diversity in Language Models: When Temperature Fails, Change the Losscited by 7
  9. 2024StreetviewLLM: Extracting Geographic Information Using a Chain-of-Thought Multimodal Large Language Modelcited by 6
  10. 2025KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphscited by 4
  11. 2025Semantic uncertainty in advanced decoding methods for LLM generationcited by 3
  12. 2020Adaptive Reinforcement Learning Model for Simulation of Urban Mobility during Crisescited by 1
3 more
  1. 2024Real-time Regulation of Detention Ponds via Feedback Control: Balancing Flood Mitigation and Water Qualitycited by 1
  2. 2025Adaptive Traffic Signal Control based on Multi-Agent Reinforcement Learning. Case Study on a simulated real-world corridorcited by 1
  3. 2025Real-time Spatial Retrieval Augmented Generation for Urban Environmentscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026HydroAgent: Formalizing Forecaster Expertise into Skill-Orchestrated Flood Forecasting Workflows
  2. 2025A RAG-Based Multi-Agent LLM System for Natural Hazard Resilience and Adaptation
  3. 2026SIREN: Towards End-to-End Extreme-Weather Early Warning with Experience-Grounded LLM Agents
  4. 2026WaterAdmin: Orchestrating Community Water Distribution Optimization via AI Agents
  5. 2024Climate Adaptation with Reinforcement Learning: Experiments with Flooding and Transportation in Copenhagen
  6. 2025Enhancing Demand-Oriented Regionalization with Agentic AI and Local Heterogeneous Data for Adaptation Planning
  7. 2026Learning long term climate-resilient transport adaptation pathways under direct and indirect flood impacts using reinforcement learning
  8. 2026Empirical Grounding Improves the Realism of LLM Agents Simulating Human Behavior During Disruptions