V-Gym is an autonomous framework that improves visual reasoning agents by iteratively updating both their skills and training data from execution experiences. It distills past trajectories into reusable procedural skills and generates targeted practice data to address identified bottlenecks, closing a loop of continual refinement. Experiments show substantial gains across several multimodal benchmarks and backbone models, with the evolved skills generalizing to new domains and models.
Visual agents improve by jointly evolving reusable skills and practice data
V-Gym turns execution trajectories into validated procedural guidance and targeted multimodal exercises, creating a feedback loop for continual refinement.
Research Lab
Bei Yan · Yuecong Min · Jie Zhang · Junqi Yang · Shiguang Shan · Xilin Chen
State Key Laboratory of AI Safety · Institute of Computing TechnologyChinese Academy of Sciences · University of Chinese Academy of Sciences
Research Digest··2 min read
In one line
V-Gym co-evolves procedural skills and multimodal practice data from agent execution trajectories for continual self-improvement.
Before you read this
Three ideas this paper builds onskill evolutionThe process of developing, refining, or optimizing reusable capabilities in LLM agents through learning, adaptation, or experience accumulation.42 papers →co-evolving feedbackFeedback that evolves alongside the policy or components it guides to improve performance.43 papers →agent skillsLearned capabilities that enable AI agents to perform specialized tasks with improved effectiveness.120 papers →
Read it as
Yan et al. introduce V-Gym, a framework that uses an agent's successful and failed visual reasoning attempts to improve both its reusable skills and its practice dataset.
The authors built an iterative system around banks of procedural skills and multimodal practice data.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.