aiqbench analysis
This paper addresses the "semantic asymmetry" bottleneck in LLM-based remote sensing agents by proposing a bidirectional retrieval method that enhances queries through planning and enriches tool representations via dependency graphs. The approach effectively bridges the gap between macro-level user intentions and fine-grained technical documentation, significantly improving retrieval accuracy on complex datasets while demonstrating robustness for general-domain transfer. For practitioners building agentic workflows, this technique offers a practical solution to context window limitations and the need for precise tool selection in specialized domains.
Bidirectional Semantic Complementary Tool Retrieval for Remote Sensing Agents
arXiv:2606.07538v1 Announce Type: cross Abstract: 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.
Abstract: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 this https URL.
Information Retrieval (cs.IR); Artificial Intelligence (cs.AI)
arXiv:2606.07538 [cs.IR]
(or arXiv:2606.07538v1 [cs.IR] for this version)
Full text under the publisher's open licence · 243 words
Related coverage
Presentation: From Models to Agents: Building Context-Aware Consumer AI at Scale at DoorDash
InfoQ · Aug 15, 2026
What's Continual Learning, and Why Might We Expect To See It In Advanced LLM Agents?
LessWrong · Jun 12, 2026
[AINews] The Future of Latent Space
Latent Space · Sep 25, 2026
FusionRS: A Large-Scale RGB-Infrared Remote Sensing Dataset for Dual-Modal Vision-Language Foundation Models
arXiv · Jun 16, 2026