Story · arXiv
RecSys Factory: Bounding LLM Agent Autonomy to Decision Points in the Industrial Recommender Lifecycle (arXiv)
paper · Story page
RecSys Factory has run for 78 days across three Tencent recommender business lines by granting the LLM autonomy only at decision points and keeping pipelines deterministic. It runs no waiting daemon, waking on host-emitted events and spending zero CPU during the 94% of wall-clock spent waiting on Spark or GPU jobs.
In plain words
- Tencent ran RecSys Factory for 78 days across three recommendation businesses, limiting free choices to specific decision points.
- Routine sequences of work stay fixed, while a language-based artificial intelligence system handles decisions needing judgment.
- The system wakes when another program reports an event, instead of running continuously while outside jobs finish.
- It used zero computer processing time during the 94% of elapsed time spent waiting on large computing jobs.
- Recommendation teams can keep flexible judgment at key moments without giving up predictable routine execution.
Appeared in
- Agent leaderboards rank specialization, and the harness thesis reaches robots
Aug 14, 2026 · in the sections
Subscribe
Get the brief in your inbox
Pick daily, weekly, or both. Nothing is gated either way: every issue is on the site and in the feeds.
- Weekdays at 8:45am IST, one lead story and 6 to 9 items.
- Sundays, an argued synthesis rather than a recap.
- One click to leave, and quiet days say so in the subject line.