Research paperRobotics & Embodied AI1 source · Oct 6, 2026

VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning

We introduce VeriFine, an agent harness framework that scales verification through the co-evolution of the policy, training curriculum, and judge.

This challenge is even more acute in embodied reasoning, where reliable evaluation must account for spatial grounding, causal reasoning, and safety-aware decision-making.
When progress plateaus and verification becomes a bottleneck, the Judge Improvement Loop selectively queries human guidance on informative failure cases and refines the judge through coactive calibration, in which humans and agents resolve disagreements and converge toward the objective rubric of physical reasoning.
Experiments on driving and robot navigation tasks demonstrate continuous self-improvement in both policy and judge capability across reinforcement and supervised fine-tuning.
These results show how scaling verification supports continuous self-improvement as policy failure patterns evolve.

[1]VeriFine: Scaling Verification for Self-Improvement in Embodied Reasoning
arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 05:50 PM
We introduce VeriFine, an agent harness framework that scales verification through the co-evolution of the policy, training curriculum, and judge.
This challenge is even more acute in embodied reasoning, where reliable evaluation must account for spatial grounding, causal reasoning, and safety-aware decision-making.

Extractive summary: sentences quoted from the sources.

Before this