UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks

• URL: http://arxiv.org/abs/2608.03018v1
• Date: Tue, 04 Aug 2026 02:04:44 GMT
• Title: UrbanAgent: A Tool-Augmented Agent for Cross-System Urban Tasks
• Abstract summary: Urban-Agent is a tool-augmented agent framework for cross-system urban tasks.<n>It couples the cognitive and reasoning capabilities of a large language model with a tool-set supporting code execution, API calls, and Model Context Protocol.<n>Experiments indicate that Urban-Agent reaches a 71% task success rate, 10 points above the strongest baseline.
• Score: 12.579199084038969
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Modern cities rely on an increasing number of digital services to operate, but residents' daily needs are still difficult to meet. Services are fragmented and have little interoperability, placing a heavy operational burden on users. Existing digital platforms, urban foundation models, and intelligent assistants each address only isolated aspects of an urban task. But they struggle to reliably convert complex natural-language requests into executable cross-system workflows. We propose Urban-Agent, a tool-augmented agent framework for cross-system urban tasks. It couples the cognitive and reasoning capabilities of a large language model with a tool-set supporting code execution, API calls, and Model Context Protocol. Through one adaptive closed loop, it clarifies missing information before acting, grounds tool use in live observations, and aligns the final response with observed evidence and task constraints. To address the evaluation gap, we introduce Urban-Eval, a benchmark specifically designed for cross-system urban request. Unlike prior benchmarks that assess either general tool use or urban knowledge and reasoning, Urban-Eval evaluates both task results and execution quality, including required tool coverage, dependency validity, and evidence traceability. Experimental results indicate that Urban-Agent reaches a 71% task success rate, 10 points above the strongest baseline. This lead holds across GPT-5-mini, Gemini-2.5-flash, DeepSeek-V4-flash, and Qwen3-235B-A22B.

Related papers

• Lingjing: A Simulation Testbed for Multi-Agent Embodied Tasks in Open-Ended Cities [19.14332737179313]
  Lingjing is a simulation platform for heterogeneous multi-agent embodied intelligence in open-ended urban environments.<n>Its Gym-like interface supports user-defined ReAct agents and single- or multi-agent natural-language missions.<n>We evaluate twelve vision-language models on nine urban tasks under a shared engine-in-the-loop protocol.
  arXiv  Detail & Related papers  (2026-08-08T10:18:58Z)
• Multi-Agent Collaborative Reasoning with Tool-Augmented Evidence for Urban Region Profiling [31.71830721319945]
  Urban region profiling supports applications such as population estimation, economic assessment, and environmental monitoring.<n>We propose UrbanAgent, an agentic framework that reframes urban region profiling as a reasoning-driven inference problem.<n>Experiments on global urban datasets for Carbon emissions, GDP, and Population estimation show that UrbanAgent consistently outperforms existing baselines.
  arXiv  Detail & Related papers  (2026-07-15T08:01:42Z)
• From Question Answering to Task Completion: A Survey on Agent System and Harness Design [67.8241530947325]
  This survey examines LLM-based agents through a model-harness lens.<n>We first clarify the functional definition of agents and the implementation view of an LLM-based agent as a foundation model and an execution harness.<n>We then analyze the limits of model-centric scaling, trace four paradigms of agent engineering, and decompose the execution harness into six coupled runtime responsibilities.
  arXiv  Detail & Related papers  (2026-06-14T05:40:16Z)
• SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks [73.92333717662558]
  SpatialWorld is a benchmark for evaluating the interactive spatial understanding of multimodal agents in complex real-world tasks.<n>It features 760 human-annotated tasks across diverse domains (e.g., household routines, travel, social collaboration)<n>For reliable evaluation, each task includes a human-validated initial state, a reference trajectory, and a terminal-state verifier.
  arXiv  Detail & Related papers  (2026-06-08T15:51:51Z)
• CITYREP: A Unified Benchmark for Urban Representations Across Cities, Tasks, and Modalities [0.8319452826580411]
  CityRep is a benchmark that evaluates urban representations across data modalities, cities, and tasks using spatially structured splits.<n>Results show that performance is highly sensitive to the split protocol, with random splits inflating scores and altering model rankings.<n>CityRep is released as a reproducible benchmark with datasets, evaluation pipelines, and diagnostic tools to facilitate fair comparison.
  arXiv  Detail & Related papers  (2026-05-25T17:03:46Z)
• DexJoCo: A Benchmark and Toolkit for Task-Oriented Dexterous Manipulation on MuJoCo [82.73355932907565]
  DexJoCo is a benchmark and toolkit for task-oriented dexterous manipulation.<n>We present 11 functionally grounded tasks that evaluate tool-use, bimanual coordination, long-horizon execution, and reasoning.<n>We benchmark modern models under diverse settings, including visual and dynamics randomization, multi-task training, and action-head adaptation.
  arXiv  Detail & Related papers  (2026-05-15T17:59:51Z)
• Urbanite: A Dataflow-Based Framework for Human-AI Interactive Alignment in Urban Visual Analytics [4.107382739138796]
  Urban visual analytics has become essential for deriving insights into pressing real-world problems.<n>The need to manage diverse datasets, distill intricate, and integrate various analytical methods presents a high barrier to entry.<n>We propose Urbanite, a framework for human-AI collaboration in urban visual analytics.
  arXiv  Detail & Related papers  (2025-08-10T15:44:37Z)
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks [64.86209459039313]
  ThinkGeo is an agentic benchmark designed to evaluate tool-augmented agents on remote sensing tasks via structured tool use and multi-step planning.<n>We implement a ReAct-style interaction loop and evaluate both open and closed-source LLMs on 486 structured agentic tasks with 1,773 expert-verified reasoning steps.<n>Our analysis reveals notable disparities in tool accuracy and planning consistency across models.
  arXiv  Detail & Related papers  (2025-05-29T17:59:38Z)
• CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space [35.223263448229716]
  Embodied Question Answering (EQA) has primarily focused on indoor environments.<n>We introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces.<n>We present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks.<n>We also propose Planner-Manager-Actor (PMA), a novel agent tailored for CityEQA.
  arXiv  Detail & Related papers  (2025-02-18T04:36:15Z)
• UrBench: A Comprehensive Benchmark for Evaluating Large Multimodal Models in Multi-View Urban Scenarios [60.492736455572015]
  We present UrBench, a benchmark designed for evaluating LMMs in complex multi-view urban scenarios.<n>UrBench contains 11.6K meticulously curated questions at both region-level and role-level.<n>Our evaluations on 21 LMMs show that current LMMs struggle in the urban environments in several aspects.
  arXiv  Detail & Related papers  (2024-08-30T13:13:35Z)
• CityX: Controllable Procedural Content Generation for Unbounded 3D Cities [50.10101235281943]
  Current generative methods fall short in either diversity, controllability, or fidelity.<n>In this work, we resort to the procedural content generation (PCG) technique for high-fidelity generation.<n>We develop a multi-agent framework to transform multi-modal instructions, including OSM, semantic maps, and satellite images, into executable programs.<n>Our method, named CityX, demonstrates its superiority in creating diverse, controllable, and realistic 3D urban scenes.
  arXiv  Detail & Related papers  (2024-07-24T18:05:13Z)
• Cross-City Matters: A Multimodal Remote Sensing Benchmark Dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks [82.82866901799565]
  We build a new set of multimodal remote sensing benchmark datasets (including hyperspectral, multispectral, SAR) for the study purpose of the cross-city semantic segmentation task. Beyond the single city, we propose a high-resolution domain adaptation network, HighDAN, to promote the AI model's generalization ability from the multi-city environments. HighDAN is capable of retaining the spatially topological structure of the studied urban scene well in a parallel high-to-low resolution fusion fashion.
  arXiv  Detail & Related papers  (2023-09-26T23:55:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.