Douyin and PKU's STEPS: agentic push filtering deployed at 1B-user scale, RecSys 2026 Oral
jiqizhixin · x · 2026-09-07
Douyin and Peking University present STEPS, a self-triggered agentic push recommendation system accepted as RecSys 2026 Oral.
Traditional push systems either poll at fixed intervals (wasting compute) or blindly trigger the full recall-rank pipeline on every event (50x more expensive than filtering). STEPS instead uses a filtering agent to first decide whether a push is worth sending at all; only approved pushes run the full recall–coarse-rank–fine-rank pipeline, turning push timing into active, context-aware judgment.
STEPS is deployed at full scale on Douyin's 1B+ user platform, with online A/B tests showing gains in user activity.
More from Research
- AFFMAE brings 5x faster high-res vision pretraining to desktop hardware, at ECCV 2026 — CSProfKGD · 2026-09-07
- lm-eval-ledger: an open-source harness to browse and compare per-question model answers — jayminban · 2026-09-07
- Detectors Were Nearly Point-Contact Diodes in 1900 — So Why Did the Transistor Take 20 More Years? — jwt0625 · 2026-09-07
- PINNStudio: Free Open-Source No-Code GUI for Physics-Informed Neural Networks — Impossible-Jello2749 · 2026-09-07
- Physics sim inches toward realism: jelly, sand deformation and water collisions — eschadiol · 2026-09-07
- Terence Tao: AI Labs Racing Math Benchmarks Are Starting to Hurt Mathematics — Old-School8916 · 2026-09-07