Meta's Auto-RecSys runs autonomous research on industry-scale recommenders
omarsar0 · x · 2026-09-11
Meta's new paper presents Auto-RecSys, a production example of autonomous research agents and harness engineering:
- Targets Meta's industry-scale recommendation models, where one training run can take days.
- Runs experiments in parallel across servers; keeps a shared memory so work survives failures and new sessions.
- Splits guidance into natural-language skill files for reasoning and deterministic scripts for operational tasks.
- Two improvement loops: model-specific playbooks log failed attempts and preserve working pipelines; experimental results feed the next round of ideas.
- As the playbook matured, major fixes per iteration fell from 4.0 to 1.3, and failures collapsed into repeatable categories.
More from coding & agent
- One-person companies are about the org chart, not headcount: humans judge, agents execute — ciguleva · 2026-10-28
- OATs: open-source toolkit turns everyday objects into personality-bearing agents — Stefania_druga · 2026-10-28
- Dev: local coding dropped from 100% to 5% in a year as cloud agents take over — bytebot · 2026-10-28
- Open-sourced 501(c)(FREE): agent-built free back office for US nonprofits — gralston · 2026-10-28
- Grok Bot 1.0.0 early build reveals Shared Bots, service accounts and team workflows — XFreeze · 2026-10-28
- Anne Griffin hosts 20-person SF salon on the product decisions behind AI agents — annetgriffin · 2026-10-28