Agentic Auto-Research is Fuzz Testing
Autonomous research agents can generate experiments faster than researchers can validate them. Researchers have responded by scaling the proposer and ranking more samples with a learned judge or human reviewers. We argue that this *generate-and-rank* paradigm misses the problem of sparse feedback. Within a declared research problem, an agent follows the control loop of a greybox fuzzer: it…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
