Evidence-Grounded Multi-Agent Planning Support for Urban Carbon Governance via RAG
On the map: LLM agents and tool use → Multimodal and embodied agents
Abstract (arXiv)
Urban carbon governance requires planners to integrate heterogeneous evidence -- emission inventories, statistical yearbooks, policy texts, technical measures, and academic findings -- into actionable, cross-departmental plans. Large Language Models (LLMs) can assist planning workflows, yet their factual reliability and evidential traceability remain critical barriers in professional use. This paper presents an evidence-grounded multi-agent planning support system for urban carbon governance built upon standard text-based Retrieval-Augmented Generation (RAG) (without GraphRAG). We align the system with the typical planning workflow by decomposing tasks into four specialized agents: (i) evidence Q&A for fact checking and compliance queries, (ii) emission status assessment for diagnostic analysis, (iii) planning recommendation for generating multi-sector governance pathways, and (iv) report integration for producing planning-style deliverables. We evaluate the system in two task families: factual retrieval and comprehensive planning generation. On factual retrieval tasks, introducing RAG increases the average score from below 6 to above 90, and dramatically improves key-field extraction (e.g., region and numeric values near 100% detection). A real-city case study (Ningbo, China) demonstrates end-to-end report generation with strong relevance, coverage, and coherence in expert review, while also highlighting boundary inconsistencies across data sources as a practical limitation.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 3 of its 9 references that are in the map. First posted on arXiv 3 Jan 2026.
Builds on
3 of 9 references.
References · 3
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
- 2024M3-Embedding: Multi-Linguality, Multi-Functionality, Multi-Granularity Text Embeddings Through Self-Knowledge Distillationcited by 1,050
- 2024The Chronicles of RAG: The Retriever, the Chunk and the Generatorcited by 34
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026Mapping and Comparing Climate Equity Policy Practices Using RAG LLM-Based Semantic Analysis and Recommendation Systems ↗
- 2025Emission-GPT: A domain-specific language model agent for knowledge retrieval, emission inventory and data analysis
- 2025Automated Evidence Extraction and Scoring for Corporate Climate Policy Engagement: A Multilingual RAG Approach
- 2024Responsible Retrieval Augmented Generation for Climate Decision Making from Documents
- 2025A Graph-Retrieval-Augmented Generation Framework Enhances Decision-Making in the Circular Economy
- 2025CarbonChat: Large Language Model-Based Corporate Carbon Emission Analysis and Climate Knowledge Q&A System
- 2026DUDA-Bench: Benchmarking LLM Agents on Multimodal Data-Driven Urban Diagnosis
- 2026AgentFAIR: A Multi-Agent Collaborative Framework for FAIRness Evaluation of Geospatial Datasets