Metraipolis › archive › dc_33920906bcd5
Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops — arXiv:2609.30297
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30297
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:38:51.240Z
- SHA-256 of the archived text
1d4e9650ae99f73a6ac25aa0de13dd18334d5de83fc0acf9fe429ec1ba7e94c2- Stable URL of this page
https://metraipolis.com/documento/dc_33920906bcd5
How to cite
Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops — arXiv:2609.30297 — arXiv (en), https://arxiv.org/abs/2609.30297 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_33920906bcd5 (Metraipolis archive dc_33920906bcd5, sha256 1d4e9650ae99f73a6ac25aa0de13dd18334d5de83fc0acf9fe429ec1ba7e94c2)
BibTeX
@misc{dc33920906bcd5,
title = {Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops — arXiv:2609.30297},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30297},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_33920906bcd5; sha256 1d4e9650ae99f73a6ac25aa0de13dd18334d5de83fc0acf9fe429ec1ba7e94c2},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30297. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Conversational recommendation agents are a new paradigm for content discovery, enabling users to express complex intents through natural language (e.g., "recommend Italian indie artists I haven't heard before"). A central challenge in building such agents is optimizing agent planning -- deciding how to select, sequence, and invoke tools -- particularly in cold-start settings where real user interactions are not yet available. We introduce a pipeline for multi-turn synthetic data generation and a self-improvement loop to address this challenge. The synthetic data pipeline transforms single-turn prompts into realistic multi-turn conversations, enabling systematic evaluation before launch. The self-improvement loop combines variance-based contrastive optimization with iterative refinement through a coding agent, automatically identifying and fixing planning and tool-use errors. Our approach improves quality by +8% on top of a highly optimized manual prompt. The system has been productionized and significantly accelerated iteration cycles for the launch of a conversational recommendation agent at Spotify. Online A/B tests demonstrate its effectiveness, with +14% user listening, +5% increase in weekly active users, and a 5% reduction in skip rate compared to a prior experience supporting only session refinement. This work provides a practical framework for accelerating the development of conversational recommendation agents in industry. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR). Pagina del lavoro: https://arxiv.org/abs/2609.30297 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-08T01:12:14.411Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).