# GeoForge: Non-Parametric Self-Evolving Agents for Earth-Observation Reasoning

arXiv: https://arxiv.org/abs/2608.10494 · HTML: https://mlsanity.com/paper/2608.10494/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Spatial and embodied reasoning, one of 17 directions in LLM reasoning.
- Builds on 19 of its 34 references that are in the map.
- First posted on arXiv 11 Aug 2026.

## Placed in

- LLM reasoning / [Spatial and embodied reasoning](https://mlsanity.com/lr/spatial-and-embodied-reasoning/)
- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)
- Synthetic data and self-improvement for LLMs / [Self-evolving LLM agents](https://mlsanity.com/synth/self-evolving-llm-agents/)

## Builds on (most cited first, 19 of 19)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation](https://mlsanity.com/paper/2308.08155/) (2023)
- [MemSkill: Learning and Evolving Memory Skills for Self-Evolving Agents](https://mlsanity.com/paper/2602.02474/) (2026)
- [Memento: Fine-tuning LLM Agents without Fine-tuning LLMs](https://mlsanity.com/paper/2508.16153/) (2025)
- [A Survey on Self-Evolution of Large Language Models](https://mlsanity.com/paper/2404.14387/) (2024)
- [XSkill: Continual Learning from Experience and Skills in Multimodal Agents](https://mlsanity.com/paper/2603.12056/) (2026)
- [Memento-Skills: Let Agents Design Agents](https://mlsanity.com/paper/2603.18743/) (2026)
- [RS-Agent: Automating Remote Sensing Tasks through Intelligent Agent](https://mlsanity.com/paper/2406.07089/) (2024)
- [ThinkGeo: Evaluating Tool-Augmented Agents for Remote Sensing Tasks](https://mlsanity.com/paper/2505.23752/) (2025)
- [Earth-Agent: Unlocking the Full Landscape of Earth Observation with Agents](https://mlsanity.com/paper/2509.23141/) (2025)
- [From Mind to Machine: The Rise of Manus AI as a Fully Autonomous Digital Agent](https://mlsanity.com/paper/2505.02024/) (2025)
- [Trajectory-Informed Memory Generation for Self-Improving Agent Systems](https://mlsanity.com/paper/2603.10600/) (2026)
- [Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism](https://mlsanity.com/paper/2511.17198/) (2025)
- [OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents](https://mlsanity.com/paper/2602.17665/) (2026)
- [TerraBench: Can Agents Reason Over Heterogeneous Earth-System Data?](https://mlsanity.com/paper/2606.13148/) (2026)
- [Experience-Driven Multi-Agent Systems Are Training-free Context-aware Earth Observers](https://mlsanity.com/paper/2602.02559/) (2026)
- [TerraLogic: A Benchmark for Hierarchical Geospatial Reasoning in Earth Observation](https://mlsanity.com/paper/2607.12497/) (2026)
- [SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory](https://mlsanity.com/paper/2605.12061/) (2026)

## Built on by (most cited first, 1 of 1)

- [RSure-Agent: Reliable Use of Tool Observations for Remote Sensing Agents](https://mlsanity.com/paper/2610.04836/) (2026)

## Abstract (arXiv)

Earth observation (EO) agents construct scientifically valid tool workflows and ground their conclusions in current geospatial evidence. This is challenging because EO workflows are constrained by sensing semantics, product dependencies, spatial and temporal compatibility, and parameter requirements. Existing agents often search a broad operation space for each query, while recent self-evolving systems do not fully organize heterogeneous EO trajectories into reusable knowledge across different decision levels. To solve this problem, we present GeoForge, a training-free, self-evolving framework that transforms completed trajectories into a structured nonparametric execution state. GeoForge constrains the operation space according to the sensing context, then retrieves a task-conditioned prior from three complementary memories. Workflow Graph Memory captures global operation order, Action-Level Experiences provide local corrections, and the Adapted Skill Standard Operating Procedure preserves procedural and data constraints. The retrieved prior guides tool execution, while current observations remain the basis of the final answer. After each task, a safety-gated distillation process converts grounded trajectories into reusable execution knowledge for future retrieval. This execution, distillation, and reuse loop improves planning without updating the backbone LLM. Experiments on multiple geospatial benchmarks demonstrate that GeoForge consistently improves both task accuracy and tool-use trajectory quality across diverse LLM backbones, while substantially reducing tool-planning and reasoning errors for most LLMs.