Science Intelligence/Research/Scientific Knowledge
§ 01 / 05 — Research direction

Scientific Knowledge

A commons of research skills — authored by human experts, executed by AI agents.

Frontier research isn’t bottlenecked by facts. It’s bottlenecked by the practical know-how of working scientists — the judgments that decide which experiment to run, the corrections for what LLMs get wrong, and the episodes of what has already failed. Scientific Knowledge is a registry of those skills, authored by researchers across disciplines and designed to be retrieved and executed by AI agents in the middle of real research runs.

§ 01.01 · Knowledge

ResearchSkills

ResearchSkills.ai is an open platform that turns real scientific workflows into reusable skills for AI agents. Instead of storing raw chat logs, it reconstructs research sessions as decision trajectories — how researchers form hypotheses, diagnose failures, choose methods, and decide when to pivot — and distills them into portable skills that agents can retrieve and execute. Contributions are extracted locally, automatically de-identified, reviewed by domain experts for scientific accuracy, and published to an open library spanning 155+ scientific subdomains under CC BY 4.0. The goal is to give AI systems not just raw capability, but the tacit research judgment that determines which experiments matter, which dead ends to avoid, and when to persist versus change direction.

§ 01.02 · Knowledge

Scaling Behaviors of LLM Reinforcement Learning Post-Training: An Empirical Study in Mathematical Reasoning

This paper systematically reveals how model scale, data volume, and compute jointly govern the scaling behavior of RL post-training for mathematical reasoning in large language models.