mlsanityData to 14 Oct 2026

Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents

arXiv 2606.07538 ↗First posted 29 Apr 2026cs.IR cs.AIcited by 1

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

Large language model (LLM)-based agents provide a novel paradigm for the automated processing of remote sensing(RS) data. Their success in complex RS tasks rely on extensive specialized tool libraries. However, tool documentation often exceeds the context window limits of LLMs, making precise tool retrieval essential for agentic workflows. Existing tool retrieval methods face "semantic asymmetry" bottleneck: natural language queries typically express macro-level intentions lacking tool-specific semantics, while tool documentation provides fine-grained technical descriptions lacking operational context for workflows. To bridge this semantic gap, this paper proposes a bidirectional semantic complementary tool retrieval method. First, on the query side, we introduce a planning-based query enhancement mechanism that leverages the reasoning capabilities of agents to decompose abstract intentions into logical subtasks, thereby actively supplementing the query with missing functional semantics. Second, on the tool side, addressing the strong coupling characteristics of RS tool chains, we construct a dynamic tool dependency graph with continual learning capabilities. By employing a neighborhood information aggregation mechanism, contextual information from precursor tools is explicitly injected into the current node representation, enriching tool descriptions with contextual semantics. Experimental results on the RS dataset GeoPlan-bench and the general-purpose dataset API- Bank demonstrate that the proposed method not only significantly improves tool retrieval accuracy for complex RS tasks but also exhibits robust extensibility for transfer to general-domain tasks. The source code and dataset are available at https://github.com/geox-lab/BSCTR.

Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 28 of its 34 references that are in the map. First posted on arXiv 29 Apr 2026.

Builds on

28 of 34 references.

Closest ancestors · 4

Same direction, newest first

  1. 2025Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism21 Nov
  2. 2025Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents27 Sep
  3. 2024RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent11 Jun
  4. 2022LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models8 Dec

Other references · 24

  1. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,695
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2023Tree of Thoughts: Deliberate Problem Solving with Large Language Modelscited by 3,211
  6. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,947
  7. 2019Simplifying Graph Convolutional Networkscited by 1,477
  8. 2023Gorilla: Large Language Model Connected with Massive APIscited by 1,332
  9. 2018Predict then Propagate: Graph Neural Networks meet Personalized PageRankcited by 993
  10. 2025DeepSeek-V3.2: Pushing the Frontier of Open Large Language Modelscited by 815
  11. 2023API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMscited by 591
  12. 2023Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Modelscited by 560
12 more
  1. 2023GeoChat: Grounded Large Vision-Language Model for Remote Sensingcited by 328
  2. 2023Tool Learning with Foundation Modelscited by 302
  3. 2024EarthGPT: A Universal Multi-modal Large Language Model for Multi-sensor Image Comprehension in Remote Sensing Domaincited by 184
  4. 2024ToolNet: Connecting Large Language Models with Massive Tools via Tool Graphcited by 60
  5. 2024Re-Invoke: Tool Invocation Rewriting for Zero-Shot Tool Retrievalcited by 52
  6. 2025SciToolAgent: A Knowledge Graph-Driven Scientific Agent for Multi-Tool Integrationcited by 43
  7. 2025Graph RAG-Tool Fusioncited by 15
  8. 2024Improving Tool Retrieval by Leveraging Large Language Models for Query Generationcited by 11
  9. 2025AutoTool: Efficient Tool Selection for Large Language Model Agentscited by 10
  10. 2025Tool Graph Retriever: Exploring Dependency Graph-based Tool Retrieval for Large Language Modelscited by 8
  11. 2025ToolDreamer: Instilling LLM Reasoning Into Tool Retrieverscited by 7
  12. 2023AllSpark: A Multimodal Spatio-Temporal General Intelligence Model with Ten Modalities via Language as a Reference Frameworkcited by 6

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026What Can Component-Replacement Evidence Establish? A Critical Scoping Review of Local Decisions in LLM Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026RS-Claw: Progressive Active Tool Exploration via Hierarchical Skill Trees for Remote Sensing Agents
  2. 2025ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks
  3. 2026SimCRAFT: Distilling Remote Sensing Agents via Synthetic Trajectories and Contextual Retrieval-Augmented Fine-Tuning
  4. 2024Evaluating Tool-Augmented Agents in Remote Sensing Platforms
  5. 2026OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents
  6. 2026RSMeM: Knowledge-Enhanced Memory Evolution for Remote Sensing Agents with Systematic Evaluation
  7. 2026SING: Synthetic Intention Graph for Scalable Active Tool Discovery in LLM Agents
  8. 2025Tool-to-Agent Retrieval: Bridging Tools and Agents for Scalable LLM Multi-Agent Systems