PhysEvolve: A Self-Evolving Framework for Physical Reasoning Driven by Executable Worlds and Verifiers

PhysEvolve proposes a verifier-grounded self-evolving framework that lets vision-language models learn causal physical reasoning from executable world programs they propose themselves and from simulation-generated tasks. In each round, a shared VLM proposes world programs and evidence schemas; a deterministic physics engine freezes each valid world and simulates matched baseline and body-elided counterfactual branches to generate discrete visual tasks; then exact verifier feedback updates the policy and curriculum via GRPO.