DEV Community

AI Tech Connect
AI Tech Connect

Posted on Originally published at aitechconnect.in

ProgramDistill Mines 4,063 Coding Tasks From 26 Live Web Apps

Originally published on AI Tech Connect.

What changed this week A new benchmark and a new pipeline. "ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks" (arXiv 2609.18805, September 2026) comes from KAIST, Microsoft Research Montreal and Microsoft AI. A dataset is published at huggingface.co/datasets/microsoft/ProgramDistill. Scale without labellers. The pipeline discovered 1,975 replay-verified behaviours across 26 applications and constructed 4,063 tasks without human intervention. Three difficulty bands. Atomic repair, cumulative repair, and full-application reconstruction — a built-in ladder rather than one undifferentiated pile of problems. Nine frontier coding agents were evaluated. On cumulative workflows within the full-application-reconstruction band, GPT-6 Astra reached 49.2% success and…


Read the full article on AI Tech Connect →

Top comments (0)