{"ID":2823028,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2601.11587","arxiv_id":"2601.11587","title":"Evidence-Grounded Multi-Agent Planning Support for Urban Carbon Governance via RAG","abstract":"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\\\u0026A 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.","short_abstract":"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 an...","url_abs":"https://arxiv.org/abs/2601.11587","url_pdf":"https://arxiv.org/pdf/2601.11587v1","authors":"[\"Yuyan Huang\",\"Haoran Li\",\"Yifan Lu\",\"Ruolin Wu\",\"Siqian Chen\",\"Chao Liu\"]","published":"2026-01-03T05:46:31Z","proceeding":"cs.CY","tasks":"[\"cs.CY\"]","methods":"[\"RAG\",\"Large Language Model\",\"Language Model\"]","has_code":false}