SOURCE-LINKED INTELLIGENCE
VisualEvolve: A Skill Self-Evolution Framework for Visual Reasoning
Visual tool use enables vision-language models (VLMs) to acquire task-relevant evidence, but its effectiveness can be limited by predefined visual operations and the tool-use strategies learned during training. Representing these operations and strategies as reusable external skills allows them to be refined through self-evolution without updating model parameters. However, skill refinement can introduce performance regressions. Meanwhile, inspecting accumulated task execution trajectories together with skill evolution history may lead to evolution evidence overload. To address these challenge
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-10-20T15:37:38.000Z
First collected: 2026-10-21T10:33:33.027Z. This is not the publication date.