SOURCE-LINKED INTELLIGENCE

VISA: Agentic Self-Evolving Data Synthesis for Multimodal Instruction Following

arXiv · AI, language, vision and robotics · article · Aug 26, 2026 · UTC

Multimodal instruction-following models require training data that is accurate, diverse, verifiable, and challenging. Existing synthesis pipelines typically follow a one-pass generate-and-filter paradigm, discarding feedback from failed samples, verifier outcomes, and target-model errors. We present VISA (Visual Instruction Synthesis Agent), an agentic framework that reformulates multimodal instruction synthesis as a self-evolving loop. At each round, VISA analyzes an image to filter incompatible constraints and discover new verifiable ones, samples diversity- and difficulty-aware constraint s

Read original source ↗ Open in workspace

recordType

paper

region

Global