# WeMusic-Agent: Efficient Conversational Music Recommendation via Knowledge Internalization and Agentic Boundary Learning

arXiv: https://arxiv.org/abs/2512.16108 · HTML: https://mlsanity.com/paper/2512.16108/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 18 Dec 2025.

## Builds on (most cited first, 30 of 30)

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [Learning without Forgetting](https://mlsanity.com/paper/1606.09282/) (2016)
- [Qwen2 Technical Report](https://mlsanity.com/paper/2407.10671/) (2024)
- [The FineWeb Datasets: Decanting the Web for the Finest Text Data at Scale](https://mlsanity.com/paper/2406.17557/) (2024)
- [CMMLU: Measuring massive multitask language understanding in Chinese](https://mlsanity.com/paper/2306.09212/) (2023)
- [The Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"](https://mlsanity.com/paper/2309.12288/) (2023)
- [Measuring short-form factuality in large language models](https://mlsanity.com/paper/2411.04368/) (2024)
- [MT-Bench-101: A Fine-Grained Benchmark for Evaluating Large Language Models in Multi-Turn Dialogues](https://mlsanity.com/paper/2402.14762/) (2024)
- [QuRating: Selecting High-Quality Data for Training Language Models](https://mlsanity.com/paper/2402.09739/) (2024)
- [A Survey on Conversational Recommender Systems](https://mlsanity.com/paper/2004.00646/) (2020)
- [Rho-1: Not All Tokens Are What You Need](https://mlsanity.com/paper/2404.07965/) (2024)
- [AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems](https://mlsanity.com/paper/2310.09233/) (2023)
- [Conversational Recommender System](https://mlsanity.com/paper/1806.03277/) (2018)
- [MAP-Neo: Highly Capable and Transparent Bilingual Large Language Model Series](https://mlsanity.com/paper/2405.19327/) (2024)
- [Evaluating the Diversity and Quality of LLM Generated Content](https://mlsanity.com/paper/2504.12522/) (2025)
- [Programming Every Example: Lifting Pre-training Data Quality Like Experts at Scale](https://mlsanity.com/paper/2409.17115/) (2024)
- [Demystifying Domain-adaptive Post-training for Financial LLMs](https://mlsanity.com/paper/2501.04961/) (2025)
- [Explainability in Music Recommender Systems](https://mlsanity.com/paper/2201.10528/) (2022)
- [CEval: A Benchmark for Evaluating Counterfactual Text Generation](https://mlsanity.com/paper/2404.17475/) (2024)
- [DistilQwen2.5: Industrial Practices of Training Distilled Open Lightweight Language Models](https://mlsanity.com/paper/2504.15027/) (2025)
- [Baichuan4-Finance Technical Report](https://mlsanity.com/paper/2412.15270/) (2024)
- [TALKPLAY: Multimodal Music Recommendation with Large Language Models](https://mlsanity.com/paper/2502.13713/) (2025)
- [Generative Product Recommendations for Implicit Superlative Queries](https://mlsanity.com/paper/2504.18748/) (2025)
- [Just Ask for Music (JAM): Multimodal and Personalized Natural Language Music Recommendation](https://mlsanity.com/paper/2507.15826/) (2025)
- [TalkPlay-Tools: Conversational Music Recommendation with LLM Tool Calling](https://mlsanity.com/paper/2510.01698/) (2025)
- [Text2Tracks: Prompt-based Music Recommendation via Generative Retrieval](https://mlsanity.com/paper/2503.24193/) (2025)
- [MuCPT: Music-related Natural Language Model Continued Pretraining](https://mlsanity.com/paper/2511.14245/) (2025)

## Built on by (most cited first, 2 of 2)

- [RecRM-Bench: Benchmarking Multidimensional Reward Modeling for Agentic Recommender Systems](https://mlsanity.com/paper/2605.11874/) (2026)
- [Autonomous Information Seeking: A Roadmap for Agentic Recommender Systems](https://mlsanity.com/paper/2607.04433/) (2026)

## Abstract (arXiv)

Personalized music recommendation in conversational scenarios usually requires a deep understanding of user preferences and nuanced musical context, yet existing methods often struggle with balancing specialized domain knowledge and flexible tool integration. This paper proposes WeMusic-Agent, a training framework for efficient LLM-based conversational music recommendation. By integrating the knowledge internalization and agentic boundary learning, the framework aims to teach the model to intelligently decide when to leverage internalized knowledge and when to call specialized tools (e.g., music retrieval APIs, music recommendation systems). Under this framework, we present WeMusic-Agent-M1, an agentic model that internalizes extensive musical knowledge via continued pretraining on 50B music-related corpus while acquiring the ability to invoke external tools when necessary. Additionally, considering the lack of open-source benchmarks for conversational music recommendation, we also construct a benchmark for personalized music recommendations derived from real-world data in WeChat Listen. This benchmark enables comprehensive evaluation across multiple dimensions, including relevance, personalization, and diversity of the recommendations. Experiments on real-world data demonstrate that WeMusic-Agent achieves significant improvements over existing models.