Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.14654 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866916910077050880 |
|---|---|
| author | Ji, Peilin Xue, Xiao Wang, Simeng Yan, Wenhao |
| author_facet | Ji, Peilin Xue, Xiao Wang, Simeng Yan, Wenhao |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_14654 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Entropy-Constrained Strategy Optimization in Urban Floods: A Multi-Agent Framework with LLM and Knowledge Graph Integration Ji, Peilin Xue, Xiao Wang, Simeng Yan, Wenhao Artificial Intelligence 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. |
| title | Entropy-Constrained Strategy Optimization in Urban Floods: A Multi-Agent Framework with LLM and Knowledge Graph Integration |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2508.14654 |