Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents

Key points

• In AI4ML, while empirical verification is available, it often requires computationally costly model training and evaluation, limiting the speed and scale of agent evolution.1
• We train the critic models through supervised fine-tuning on high-quality critiques synthesized by Gemini-3.1-Pro, followed by GRPO to further improve their predictive accuracy.1
• Empirically, our critic models outperform Gemini-3.1-Pro in static idea evaluation, and these gains extend to agent inference, continual learning, and policy training.1
• Together, these results show that idea-level critic models help ML agents discover better solutions and learn stronger proposal policies under limited verification budgets.1

Sources (1)

• [1]Verify Less, Evolve More: Training Idea-Level Critics for Verification-Efficient ML Evolving Agents
  arXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 6, 06:52 PM

  As large language models become more powerful, self-evolving agents are able to tackle challenging tasks including AI for machine learning (AI4ML).

  In AI4ML, while empirical verification is available, it often requires computationally costly model training and evaluation, limiting the speed and scale of agent evolution.

Extractive summary: sentences quoted from the sources.