Driving Scientific Discovery with Evolutionary Search
ParshinShojaee · x · 2026-07-17
This post discusses the concept of search as a driver for scientific discovery.
The core arguments are:
- LLMs already possess vast scientific knowledge, akin to a researcher who has "read almost every paper"
- However, "discovery" isn't about reciting existing knowledge, but finding things beyond it
- Therefore, evolutionary search—continuously generating and filtering hypotheses through "mutation + recombination"—is a natural and effective way to push models out of their knowledge bubbles
- While leveraging the model's existing scientific priors, the ultimate goal is to advance open-ended scientific discovery
The context also mentions the author has successfully defended their PhD, with a dissertation titled 《Steps Toward Open-Ended Reasoning and Discovery with Language Models》, focusing on how LLMs can engage in open-ended reasoning and discovery, and what is currently missing.
Related event: Parshin Shojaee Shares PhD Thesis on Open-Ended LLM Discovery(5 posts)→
More from Research
- rauchg reproduces OpenAI's covert CPU-channel finding: chat across Firecracker microVMs with no network — ccerrato147 · 2026-10-27
- Microsoft Research: ForkPilot cuts long-horizon agent compute by up to 59% — EliasEskin · 2026-10-27
- Microsoft's TeleTune evolves agent skills from offline user telemetry — EliasEskin · 2026-10-27
- FlexGlue: sparse-to-dense matching that beats dense accuracy at a fraction of the cost — zhenjun_zhao · 2026-10-27
- Mundo turns a few room photos into an explorable, simulatable 3D world — at 1.5 FPS — mark_k · 2026-10-27
- Mathematics as an experimental science: Marc Lelarge to talk LLM-driven math experiments at ENS — marc_lelarge · 2026-10-27