AutoResearch: Turning a Research Loop into a Falsifiable System

The interesting part of AutoResearch is not a claim that an agent has suddenly become a scientist. It is the discipline of turning research into an auditable loop: propose a change, run an experiment, read evaluator-owned evidence, retain or reject an artifact, and choose the next experiment. That loop is useful. By itself, however, it is neither a benchmark nor evidence of recursive self-improvement (RSI).

1. Four Things That Must Stay Separate

Karpathy’s autoresearch is a clean prototype. The agent edits a constrained training script while preparation and evaluation stay frozen; short runs return a metric and the loop keeps better candidates. It demonstrates bounded empirical optimization. It does not claim cross-hardware comparability, general scientific competence, or RSI.

2. What Sits Between Code Editing and Research

A research loop needs answers to four questions:

1. What is the intervention? Which files, hyperparameters, tool calls, or experimental designs may change?
2. Where does evidence come from? Visible development metrics, a sealed verifier, physical constraints, or human feedback?
3. What is retained? Only the final best artifact, or hypotheses, failed trials, and a decision lineage?
4. How is local optimization ruled out? Is the evaluator frozen, and are selected results rerun on held-out seeds, settings, or an independent runtime?

Without the fourth answer, the honest label is usually “optimization of a local harness,” not research. A stronger claim puts evaluator code, data preparation, and hidden tests behind a write boundary, then reruns winners on preregistered held-out settings.

3. Scientific Tasks Can Measure Different Objects

This is not a ranking of which system is “more scientific.” MLS-Bench fixes the algorithmic axis and asks for cross-setting evidence. AutoLab centers wall-clock budget and empirical iteration. EdgeBench studies how feedback becomes a better artifact over at least twelve hours. Terminal-Bench Science is still under construction; it should not be cited as a released, complete benchmark.

4. A Research Card Worth Publishing

I would report a serious AutoResearch experiment with this card, not a single attractive trajectory:

The pivotal ablation removes experimental lineage while keeping model, tools, and budget fixed. Only when the advantage disappears is there evidence that the loop learned from its history rather than merely sampled a lucky candidate.

5. When RSI Is an Appropriate Claim

RSI concerns the system that performs the next round of research, not merely the current target. A system that changes its own tool selection, context policy, search program, or agent policy, then performs better on sealed tasks it did not select against, approaches empirical evidence for RSI. Darwin Gödel Machine is a serious direction to study; its experimental results are still not a proof of unbounded recursive improvement.

I therefore use deliberately conservative labels:

• Improving an external artifact: automated target optimization.
• Reusing experimental history to improve continuously: AutoResearch / autonomous research loop.
• Improving the agent or harness that runs future loops, with gains preserved on sealed, shifted evaluations: empirical evidence for RSI.

6. Where to Go Next

1. Environments: what artifacts, feedback, and verifiers different research tasks actually hold an agent accountable for.
2. Agentic RL: why a training system must preserve the behavior of the real harness.
3. RSI: when it is justified to move from optimizing a target to improving the improver.