Training a 4B model to produce 81% faster query plans than Postgres

In one line

…or how to make Qwen learn query optimization via agentic reinforcement learning

Opening excerpt

Four RL rollouts commence for a single query. Qwen produces a candidate strategy per rollout and sends it off to Postgres for measurement against its own default plan. Scalar rewards are assigned to each rollout, which flow backwards to update Qwen’s weights.

Leis et al. asked this exact question in 2015. Then, they asked it again 10 years later .

Despite an enormous body of research spanning a decade since their original exploration, they found that query optimizers continue to leave much to be desired.

I was surprised when I first learned about this. A Postgres database should know everything about the stuff that lives in its tables, no? How hard can it be?

(Excerpted from the original; full article via the source link below.)

This story hit the Hacker News front page today (247 points / 41 comments, via rohanbansal.com). Our Tech Radar aggregates daily signals on AI engineering, backend architecture and DevOps — browse the related services and further reading below, or get in touch with our team.