# Unleash the Potential of Long Semantic IDs for Generative Recommendation

arXiv: https://arxiv.org/abs/2602.13573 · HTML: https://mlsanity.com/paper/2602.13573/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 14 Feb 2026.

## Built on by (most cited first, 4 of 4)

- [Learning from Unreachable Rewards: Hint-Conditioned Reinforcement Learning for Generative Recommendation](https://mlsanity.com/paper/2608.11980/) (2026)
- [PRQ-KMeans: Projection Residual Quantization for Semantic ID Tokenization](https://mlsanity.com/paper/2608.24207/) (2026)
- [SIDScope: A Diagnostic Resource for Semantic-ID Interfaces in Generative Recommendation](https://mlsanity.com/paper/2608.18779/) (2026)
- [Preference Shapes Relevance: Cross-component Hierarchical Semantic Alignment for Personalized Generative Retrieval](https://mlsanity.com/paper/2608.30553/) (2026)

## Abstract (arXiv)

Semantic ID-based generative recommenders face a granularity-efficiency dilemma between efficient recommendation with short IDs and expressive item modeling with long IDs. To break this dilemma, we propose ACERec, a framework that preserves the semantic richness of long IDs while keeping the recommendation process efficient. Concretely, ACERec employs an Attentive Token Merger to compress long semantic IDs into compact yet faithful latent tokens. To better capture user intent from the compressed semantics, we further introduce a dedicated Intent Token, optimized by a dual-granularity objective that combines token-level generation with item-level intent-semantic alignment. Extensive experiments on nine real-world benchmarks show that ACERec consistently outperforms state-of-the-art methods, yielding average relative improvements of 12.92% in NDCG@10 and 7.49% in Recall@10 over the strongest baselines.