Techniques

Automated AI research

Technique · Agents · 2 items since Apr 2026

Agents that run AI research themselves: proposing ideas, running experiments, and reporting results.

Related

Organizations
AnthropicNVIDIA
Techniques
Harness optimizationWeak-to-strong generalization

Trends

Items

  1. Sep 18

    NVIDIA's SoL-Pi automates harness research

    Scaling automated auto-research loops at the agent-harness layer yields four transferable mechanisms that match the Pi harness on the 51-task EdgeBench while cutting recorded token traffic 44.7-49.0% and API cost by about a third.

  2. Apr 14

    Anthropic's Automated Alignment Researchers

    Claude agents autonomously developed, implemented, and evaluated ideas on the weak-to-strong supervision problem, recovering a meaningful share of the performance gap without human guidance on each experiment, the first empirical evidence that LLM agents can speed up alignment research.