# TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling

arXiv: https://arxiv.org/abs/2510.01698 · HTML: https://mlsanity.com/paper/2510.01698/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Oct 2025.

## Built on by (most cited first, 5 of 5)

- [WeMusic-Agent: Efficient Conversational Music Recommendation via Knowledge Internalization and Agentic Boundary Learning](https://mlsanity.com/paper/2512.16108/) (2025)
- [A Unified Language Model for Large Scale Search, Recommendation, and Reasoning](https://mlsanity.com/paper/2603.17533/) (2026)
- [TwiSTAR:Think Fast, Think Slow, Then Act,Generative Recommendation with Adaptive Reasoning](https://mlsanity.com/paper/2605.11553/) (2026)
- [DialBGM: A Benchmark for Background Music Recommendation from Everyday Multi-Turn Dialogues](https://mlsanity.com/paper/2604.07895/) (2026)
- [Bootstrapping Conversational Recommendation Agents At Spotify: Synthetic Data Generation and Self-Improvement Loops](https://mlsanity.com/paper/2609.30297/) (2026)

## Abstract (arXiv)

While the recent developments in large language models (LLMs) have successfully enabled generative recommenders with natural language interactions, their recommendation behavior is limited, leaving other simpler yet crucial components such as metadata or attribute filtering underutilized in the system. We propose an LLM-based music recommendation system with tool calling to serve as a unified retrieval-reranking pipeline. Our system positions an LLM as an end-to-end recommendation system that interprets user intent, plans tool invocations, and orchestrates specialized components: boolean filters (SQL), sparse retrieval (BM25), dense retrieval (embedding similarity), and generative retrieval (semantic IDs). Through tool planning, the system predicts which types of tools to use, their execution order, and the arguments needed to find music matching user preferences, supporting diverse modalities while seamlessly integrating multiple database filtering methods. We demonstrate that this unified tool-calling framework achieves competitive performance across diverse recommendation scenarios by selectively employing appropriate retrieval methods based on user queries, envisioning a new paradigm for conversational music recommendation systems.