SynthRL: Scaling Visual Reasoning with Verifiable Data Synthesis

Le résumé fourni par la source

Vision-language models (VLMs) trained via reinforcement learning with verifiable reward (RLVR) have shown notable progress in scaling test-time compute effectively.In this work, we investigate how synthesized RL data can further improve RLVR.To this end, we propose Syn-thRL-a scalable and guaranteed pipeline for automatic data scaling in reasoning-oriented RL training.SynthRL comprises three key stages: (1) selecting seed questions with appropriate distribution, (2) augmenting them into more challenging variants while preserving the original answers, and (3) a guaranteed verification stage that ensures near-perfect correctness and difficulty enhancement.Our empirical experiments demonstrate SynthRL's scalability and effectiveness.When applied to the MMK12 dataset, SynthRL synthesizes over 3.3K additional verifiable, challenging questions from approximately 8K seed samples.Models trained with our synthesized data achieve consistent gains across five outof-domain visual math reasoning benchmarks, with a significant improvement over baseline models trained on seed data alone.Notably, detailed analysis reveals that the gains are more pronounced on the most challenging evaluation samples, highlighting SynthRL's effectiveness in eliciting deeper and more complex reasoning patterns.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.