Auto Research

Auto Research is the research-automation layer defined in 171: 【AI季报 26Q2】从 coding 到 RSI，强者愈强的未来？ as AI acting like a researcher: reading papers, forming hypotheses, writing code, running experiments, and analyzing results. It overlaps with ML Coding, Deep Research, and Discovery Model, but the episode uses it specifically as the step before Recursive Self-Improvement.

The distinction matters. Auto Research can make human researchers faster without proving that the system improves itself. Recursive Self-Improvement requires the research loop to improve the next round of model, data, training recipe, benchmark, verifier, or agent system.

Key Claims

• Auto Research needs long-horizon planning, paper reading, experiment coding, execution, analysis, and iteration.
• Code is the first strong substrate because experiments, data pipelines, benchmark harnesses, and evaluation scripts are executable and reviewable.
• The bottlenecks shift toward AI Coding Verification, AI Verification, Research Taste, compute allocation, and whether the task is worth optimizing.
• Auto Research can contribute to AI For Science even before it becomes full RSI.
• Startup and frontier-lab claims in this area should be treated as loop-quality claims, not just benchmark-score claims.

Connections

• Recursive Self-Improvement — stronger loop that Auto Research may enable.
• ML Coding — coding-heavy version of AI research work.
• Deep Research, Discovery Model, and AI For Science — adjacent research and discovery frames.
• Recursive and Anthropic — source examples tied to auto-research and RSI practice.
• AI Coding Verification, AI Verification, and Research Taste — controls needed to keep automated research useful.