Microsoft's ProgramDistill turns interactive web apps into verifiable SWE training tasks
_akhaliq · x · 2026-09-27
Microsoft's Debug Gym team released ProgramDistill, a pipeline that converts interactive web apps into verifiable, reference-guided software engineering tasks for training and benchmarking coding agents.
Companion resources include the arXiv paper, a blog post, the ProgramDistill-Bench dataset on Hugging Face, and a public leaderboard.
It offers a new recipe for generating large-scale, gradable SWE tasks for agent training and evals.
More from coding & agent
- Devs Are Just Yes Machines Now: Complaining About Claude Extension's Constant Prompts in VS Code — ThePeterMick · 2026-09-27
- Routing Evals Are Missing, Says Elvis Saravia as OpenRouter Criticism Rages Without Evidence — omarsar0 · 2026-09-27
- Opus 5.5 prompt turns code-rendered frames into an epic 'History of Chinese Civilization' film — dotey · 2026-09-27
- Meta's Muse gives every user their own VM, called the most careful consumer agent sandbox yet — AccBalanced · 2026-09-27
- SafeScript: a Turing-incomplete JS subset lets agent policies replace code review — uriwa · 2026-09-27
- Open source AI-SQL engine Quail signals shift toward cheap task-specific models — sh_reya · 2026-09-27