RLVR-trained small model fixes 83.7% of LaTeX errors, 6x faster at 1/40 the cost

simonguozirui · x · 2026-09-17

Tinker (Sundial) fine-tuned thinkymachines' Inkling-Small with RLVR to fix LaTeX compile errors directly inside the editor: 83.7% fix rate on real errors, matching Claude Fable 5.1 while being 6x faster and 1/40 the cost ($0.0013 per fix), responding in under a second.

Their training emphasized getting RLVR right:

The motivation came from interviews with mathematicians, whose top daily annoyance was battling LaTeX compilation errors. Asking a chatbot works decently, but switching windows breaks writing flow, and copy-pasting snippets loses context—especially across multiple files. They scraped 272,000 questions from TeX.StackExchange and kept 3,978 with usable snippets as training data.

Original post →

More from coding & agent

coding & agent channel →