RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents

cs.CV

Submitted: 2026-10-04

Updated: 2026-10-04

Comments: The demo is available at https://github.com/airs101/RSure-Agent (code will be released for further research)

Code: https://github.com/airs101/RSure-Agent

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers
• Agentic AI for Remote Sensing: Technical Challenges and Research Directions
• ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks
• TerraLogic: A Benchmark for Hierarchical Geospatial Reasoning in Earth Observation
• Tree-GPT: Modular Large Language Model Expert System for Forest Remote Sensing Image Understanding and Interactive Analysis
• RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing
• REMSA: Foundation Model Selection for Remote Sensing via a Constraint-Aware Agent
• OpenEarth-Agent: From Tool Calling to Tool Creation for Open-Environment Earth Observation
• GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning
• MineAgent: Towards Remote-Sensing Mineral Exploration with Multimodal Large Language Models
• Towards LLM Agents for Earth Observation
• TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?
• A Survey on Trustworthy LLM Agents: Threats and Countermeasures
• AgentLTL: A Trace-Verification Framework for Measuring, Enforcing, and Training Procedural Compliance in Tool-Using LLM Agents
• Verified Tool Calls Improve LLM Agent Reliability Under Non-Atomic Failures
• Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs
• CangLing-KnowFlow: A Unified Knowledge-and-Flow-fused Agent for Comprehensive Remote Sensing Applications
• Auditing Automated Evaluation, Error Propagation, and Runtime Mitigation in Tool-Using Language Agents
• When the Tool Decides: LLM Agents Defer Blindly to Graph Neural Network Tools, and Stronger Backbones Defer More
• ToolGate: Token-Efficient Pre-Call Control for Tool-Augmented Vision-Language Agents

Related papers

• Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
• AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
• Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
• MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
• TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
• A Survey on Efficient Vision-Language-Action Models