ByteDance Deploys SequenceO1 at Full Traffic on Douyin, Compressing 100K-Long User Histories for Recommendation

_reachsumit · x · 2026-09-09

ByteDance introduces SequenceO1, an end-to-end framework for ultra-long (100K interaction) user behavior sequence modeling in recommendation, deployed at full traffic on Douyin.

The design follows a compress-then-reason approach:

The paper argues that at 100K scale the challenge goes beyond attention complexity: prior approaches (truncation, multi-stage retrieval, compressed lifelong histories, short-train/long-infer extrapolation) either weaken end-to-end optimization or retain length-dependent cost. The cacheable sketch enables deployment under strict latency, memory, communication, and training-throughput constraints.

Original post →

More from Research

Research channel →