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

arXiv: https://arxiv.org/abs/2508.14654 · HTML: https://mlsanity.com/paper/2508.14654/

## 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.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 15 of 15)

- [Turning Up the Heat: Min-p Sampling for Creative and Coherent LLM Outputs](https://mlsanity.com/paper/2407.01082/) (2024)
- [Predicting Question-Answering Performance of Large Language Models through Semantic Consistency](https://mlsanity.com/paper/2311.01152/) (2023)
- [SCORE: Systematic COnsistency and Robustness Evaluation for Large Language Models](https://mlsanity.com/paper/2503.00137/) (2025)
- [Adaptive Traffic Signal Control: Deep Reinforcement Learning Algorithm with Experience Replay and Target Network](https://mlsanity.com/paper/1705.02755/) (2017)
- [SafeLight: A Reinforcement Learning Method toward Collision-free Traffic Signal Control](https://mlsanity.com/paper/2211.10871/) (2022)
- [HyperTree Planning: Enhancing LLM Reasoning via Hierarchical Thinking](https://mlsanity.com/paper/2505.02322/) (2025)
- [KG-Retriever: Efficient Knowledge Indexing for Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2412.05547/) (2024)
- [Improving Diversity in Language Models: When Temperature Fails, Change the Loss](https://mlsanity.com/paper/2508.09654/) (2025)
- [StreetviewLLM: Extracting Geographic Information Using a Chain-of-Thought Multimodal Large Language Model](https://mlsanity.com/paper/2411.14476/) (2024)
- [KG-Infused RAG: Augmenting Corpus-Based RAG with External Knowledge Graphs](https://mlsanity.com/paper/2506.09542/) (2025)
- [Semantic uncertainty in advanced decoding methods for LLM generation](https://mlsanity.com/paper/2506.17296/) (2025)
- [Adaptive Reinforcement Learning Model for Simulation of Urban Mobility during Crises](https://mlsanity.com/paper/2009.01359/) (2020)
- [Real-time Regulation of Detention Ponds via Feedback Control: Balancing Flood Mitigation and Water Quality](https://mlsanity.com/paper/2403.04675/) (2024)
- [Adaptive Traffic Signal Control based on Multi-Agent Reinforcement Learning. Case Study on a simulated real-world corridor](https://mlsanity.com/paper/2503.02189/) (2025)
- [Real-time Spatial Retrieval Augmented Generation for Urban Environments](https://mlsanity.com/paper/2505.02271/) (2025)

## 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.