Microsoft's TeleTune evolves agent skills from offline user telemetry
EliasEskin · x · 2026-10-27
TeleTune, a Microsoft Research project from an internship effort by UNC's Justin Chen, learns reusable computer-use agent skills from offline user telemetry. The paper argues telemetry is a scalable source of procedural software-usage knowledge, but extracting skills requires addressing challenges like goal underspecification, since logs don't record the user's intent. Authors include Justin Chih-Yao Chen, Elias Stengel-Eskin, Ben Van Durme, and Harsh Jhamtani (October 2026).
More from Research
- UK AISI: under $80 of fine-tuning fully restores filtered bio capabilities in open-weight models — connoraxiotes · 2026-10-27
- RFD4-Proteina runs on an RTX 3060: protein design from $0.001 per design — AllThingsApx · 2026-10-27
- University of Freiburg's Generative Intelligence Lab recruiting funded PhDs via ELLIS, apply by Oct 31 — yuyinzhou_cs · 2026-10-27
- Nature Physics: reprogrammable refractive index enables arbitrary multimode wave control for ML — MarioKrenn6240 · 2026-10-27
- Wakaru open-sources ontologize: labeling datasets from model activations — amplifiedamp · 2026-10-27
- EMNLP Oral paper traces multilingual representations in LLMs with cross-layer transcoders — ZhijingJin · 2026-10-27