GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents

Han Luo; Xian Xu; Yinhe Liu; Yanfei Zhong

cs.AISep 12, 2026

GeoSkill:Experience-Driven Hierarchical Skill Learning with Collaborative Revision forGeospatialAgents

Authors: Han Luo, Xian Xu, Yinhe Liu, Yanfei Zhong

Organizations: Wuhan University

Abstract

Geospatial agents are increasingly expected to support recurring and evolving analytical tasks rather than execute isolated workflows. In such settings, effective agents must distill prior execution experience into reusable geospatial procedural knowledge to guide future planning and tool use. However, existing memory-augmented paradigms struggle to summarize both long-horizon tool-chain orchestration experience and tool-level invocation constraints in geospatial analysis, while directly relying on LLM self-reflection to update experience often leads to misattribution and unreliable revisions. To address these challenges, we propose GeoSkill, an experience-driven hierarchical skill learning framework for geospatial agents. GeoSkill comprises two core components: (i) a Hierarchical Skill Bank (HSB), consisting of a Planning Skill Bank and a Tool Skill Bank, which respectively distill high-level task-planning experience and tool usage constraints, enabling structured representation and cross-task reuse of historical execution experience; and (ii) a Collaborative Trace-driven Skill Revision (CTSR) mechanism, where Judge, Critic, and Refiner collaboratively perform error identification, skill-level defect localization, and targeted modification, preventing misattributed and unreliable revisions from polluting the skill bank. GeoSkill learns and validates skills from historical executions during development, and freezes the skill bank for retrieval-only guidance on unseen tasks during deployment. Extensive experiments on EarthBench and ThinkGeo demonstrate that GeoSkill effectively transforms historical execution experience into reusable hierarchical skills, improving both end-to-end task accuracy and tool-execution reliability in geospatial tasks.

Figures & tables

Figure 1: Comparison of agent paradigms illustrated with an LST (Land Surface Temperature) analysis task. (a) Independent Execution : each task runs a standalone ReAct loop from scratch; experience is lost and wrong data/tool selections repeat across tasks. (b) Intra-task Reflexion : verbal reflections repair the current trial, but the experience is not transferred to future tasks. (c) Inter-task Memory : experiences are extracted into a flat pool (e.g., “Use LST product”), yet critical constraints such as spatial resolution and temporal requirements are missing, causing downstream failures. (d) Hierarchical Skill Evolution (Ours) : a Hierarchical Skill Bank separates planning skills (LST analysis workflow) from tool skills (LST product constraints), while Causal Trace-driven Skill Revision evolves them through validated edits, preserving both workflow structure and execution constraints.

Figure 2: Overview of the GeoSkill framework. During development (top), GeoSkill iteratively evolves a Hierarchical Skill Bank (HSB) through a Retrieve–ReAct–Revise–Retain loop. The HSB decomposes procedural memory into Planning Skills and Tool Skills. Upon execution failure, a Causal Trace-driven Skill Revision (CTSR) pipeline—Judge (failure attribution), Critic (trace analysis and defect localization), and Refiner (constraint-preserving targeted revision)—diagnoses and repairs defective skills. Revised candidates are retained only after successful re-execution. During deployment (bottom), the skill bank is frozen and retrieved skills guide execution on unseen tasks without further updates.

		EarthBench						ThinkGeo
Backbone	Method	Acc.	Eff.	Tool Calling			Param.	POL (F1)			Ans_T	Ans_I
Backbone	Method	Acc.	Eff.	Any	In-Ord.	Exact	Param.	P	O	L	Ans_T	Ans_I
DeepSeekV4Pro	ReAct	58.06	6.69	81.88	71.35	58.37	27.50	59.47	71.26	41.88	37/185	29/33
	ReAct@3	66.94	12.85	78.28	69.64	57.17	27.88	61.07	72.34	44.26	52/185	30/33
	Reflexion	73.98	12.93	78.08	70.49	57.02	27.82	53.94	57.39	39.10	52/185	31/33
	ExpeL	65.32	8.50	73.50	64.00	52.00	23.50	55.00	58.00	40.50	41/188	28/30

Table 1: Main results on EarthBench and ThinkGeo. Red = best per backbone, blue = second best.

HSB	CTSR	Acc	Eff	Any	Exact	Param	In-Ord
$\times$	$\times$	65.32	8.50	73.50	52.00	23.50	64.00
$\checkmark$	$\times$	72.58	7.25	80.12	55.80	25.90	69.45
$\checkmark$	$\checkmark$	79.03	6.08	84.54	58.37	27.50	73.91

Table 2: Ablation of GeoSkill components (EarthBench, DSV4-Pro).

Panel of Figure 3 — Figure 3: Effect of revision rounds on EarthBench (DeepSeek-V4-Pro). $B{=}0$ is retrieval-only without revision.

LLM Agent Skill Learning

Large language model agent skill learning studies how agents acquire, represent, reuse, and refine procedures for multi-step tasks.

See all 402 papers

Oct 12, 2026

EvoSpatial: Experience-Driven Skill and Tool Evolution for Spatial Reasoning Agents

Spatial reasoning agents can inspect tool outputs and repair errors, but reusing these lessons requires preserving both the computation and the conditions that make it valid. We introduce EvoSpatial, a framework that learns from execution experience by updating a library of linked skills and tools. Skills describe procedures, geometric assumptions, and verification steps; tools implement the operations those procedures require. When solving a task, the agent retrieves relevant skills and synthesizes reusable computational functions if existing tools are insufficient. After each task, execution feedback and evidence checks guide skill revision and tool consolidation, without ground-truth answers or benchmark scores. Across 20 benchmarks, EvoSpatial averages 63.9, 4.0 percentage points above the average reported by SpatialClaw. The evolved library also improves held-out and cross-benchmark performance when updates are disabled, and trajectories generated with evolved skills improve supervised fine-tuning, even without external skills at evaluation. Keeping checked procedures on record, together with the tools that support them, lets an agent carry spatial reasoning experience from one task to the next.

Bin Yu, Shijie Lian, Zhaolong Shen +10

Harbin Institute of Technology · Zhongguancun Academy · DeepCybo +5

Tool-Using Agents Spatial Reasoning Visual Spatial Reasoning Agent Skill Learning Self-Evolving Agents Memory-Augmented Agents

Ask PDF

Aug 11, 2026

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

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.

Xin Xiao, Jiang Zhong, Junnan Zhu +4

School of Computer Science, Chongqing University · MAIS, Institute of Automation, Chinese Academy of Sciences · Aerospace Information Research Institute, Chinese Academy of Sciences

Agent Memory Geospatial Reasoning LLM Agent Planning Self-Evolving Agents

Ask PDF

Apr 10, 2026

Skill-Conditioned Visual Geolocation for Vision-Language Models

Vision-language models (VLMs) have shown a promising ability in image geolocation, but they still lack structured geographic reasoning and the capacity for autonomous self-evolution. Existing methods predominantly rely on implicit parametric memory, which often exploits outdated knowledge and generates hallucinated reasoning. Furthermore, current inference is a "one-off" process, lacking the feedback loops necessary for self-evolution based on reasoning outcomes. To address these issues, we propose GeoSkill, a training-free framework based on an evolving Skill-Graph. We first initialize the graph by refining human expert trajectories into atomic, natural-language skills. For execution, GeoSkill employs an inference model to perform direct reasoning guided by the current Skill-Graph. For continuous growth, an Autonomous Evolution mechanism leverages a larger model to conduct multiple reasoning rollouts on image-coordinate pairs sourced from web-scale data and verified real-world reasoning. By analyzing both successful and failed trajectories from these rollouts, the mechanism iteratively synthesizes and prunes skills, effectively expanding the Skill-Graph and correcting geographic biases without any parameter updates. Experiments demonstrate that GeoSkill achieves promising performance in both geolocation accuracy and reasoning faithfulness on GeoRC, while maintaining superior generalization across diverse external datasets. Furthermore, our autonomous evolution fosters the emergence of novel, verifiable skills, significantly enhancing the system's cognition of real-world geographic knowledge beyond isolated case studies.

Chenjie Yang, Yutian Jiang, Yutong Deng +1

Southwest Jiaotong University Chengdu, China · The Hong Kong University of Science and Technology (Guangzhou) Guangzhou, China · Zhejiang University Hangzhou, China

VLM Reasoning Vision-Language Models Faithfulness in VLMs

Ask PDF

Abstract

LLM Agent Skill Learning

Explore similar work

EvoSpatial: Experience-Driven Skill and Tool Evolution for Spatial Reasoning Agents

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

Skill-Conditioned Visual Geolocation for Vision-Language Models