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 a...
| Authors | Bin Yu, Shijie Lian, Zhaolong Shen et al. |
|---|---|
| Primary category | cs.CV |
| Published | 12 October 2026 |
| Last updated at source | 14 October 2026 |
Recent changes
- 15 Oct 2026 Description: Tool-augmented vision-language agents compose perception and measurement to reason about spatial relationships, but effective execution also requires tracking geometric assumptions and checking intermediate evidence. Preserving this experie → 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 e
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 15 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.