Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops

The paper presents a pipeline for generating multi‑turn synthetic conversations and a self‑improvement loop that uses variance‑based contrastive optimization and a coding agent to refine planning and tool‑use in conversational recommendation agents. This approach improves agent quality by 8% over a manually optimized prompt and has been deployed at Spotify, where it accelerated development cycles. In production, the system achieved a 14% increase in user listening, a 5% rise in weekly active users, and a 5% reduction in skip rate compared to a prior session‑only experience.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents
• data-engineering