arXiv Computation and Language November 6, 2026 By Hongyang Su, Beibei Kong, Lei Cheng, Chengxiang Zhuo, Zang Li

Do Recommenders Need to Think in Words? Latent Reasoning for Efficient LLM-Based Recommendation

Read the original on arXiv Computation and Language →

The paper introduces LatentRec, a framework that replaces inference-time chain-of-thought reasoning in large language model (LLM) recommender systems with training-time per-step supervision. It employs a 2.5 M-parameter Continuous Thought Module, Soft Token Selection, and a Per-step Reasoning Loss to guide intermediate hidden states toward the target semantic ID. After training, the module can be removed, yielding a 4–5 % relative improvement in HR@10 on Amazon benchmarks while reducing inference latency by 18.3×.

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 Computation and Language.

Hugging Face Trending Papers

1d ago

Do Recommenders Need to Think in Words? Latent Reasoning for Efficient LLM-Based Recommendation

LLM-based recommender systems increasingly generate chain-of-thought (CoT) text before each item prediction to activate the LLM's reasoning capacity, costing tens to hundreds of extra tokens per recom...

llms rag benchmarks

arXiv AI

Sep 30

OneLatent: Latent Reasoning for Efficient Foundation Recommendation Models

arXiv:2607.26621v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their use as the backbone of foundation recommendati...

By Hao Jiang, Peiru Du, Pengfei Yao, Mengting Li, Siyuan Lou, Kuo Cai, Sheng Yu, Qiang Luo, Jian Liang, Ruiming Tang, Fei Pan, Peng Jiang, Wenwu Ou

llms efficiency benchmarks safety

arXiv AI

Jul 31

WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models

arXiv:2607. 26621v2 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong reasoning capabilities, motivating their adoption as backbones for foundation recommendation models (FRMs).

By Hao Jiang, Peiru Du, Pengfei Yao, Mengting Li, Siyuan Lou, Kuo Cai, Sheng Yu, Qiang Luo, Jian Liang, Ruiming Tang, Fei Pan, Peng Jiang, Wenwu Ou

llms diffusion efficiency benchmarks safety

arXiv AI

Jul 21

Training Continuous Chain of Thought Models: A Tale of Two Regimes

arXiv:2607. 16972v1 Announce Type: new Abstract: Continuous Chain-of-Thought methods replace verbose reasoning traces with a short sequence of dense latent representations.

By Varun Yerram, He He, Eunsol Choi

rag

arXiv AI

Jun 15

Implicit Reasoning for Large Language Model-based Generative Recommendation

arXiv:2606. 14142v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world knowledge.

By Yinhan He, Liam Collins, Bhuvesh Kumar, Jundong Li, Neil Shah, Donald Loveland

llms rag safety

arXiv AI

Jun 16

Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate

arXiv:2606. 16360v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting improves reasoning in large language models (LLMs) by externalizing intermediate computation as discrete text tokens, but this textual interface also introduces redundancy and inference overhead.

By Hanyu Lin, Min Cai, Jiawei Wen, Haodi Zhang

llms

One email a morning, machine-written

Related stories

Do Recommenders Need to Think in Words? Latent Reasoning for Efficient LLM-Based Recommendation

OneLatent: Latent Reasoning for Efficient Foundation Recommendation Models

WhisperRec: Latent Reasoning for Efficient Foundation Recommendation Models

Training Continuous Chain of Thought Models: A Tale of Two Regimes

Implicit Reasoning for Large Language Model-based Generative Recommendation

Tyler: Typed Latent Reasoning for Language Models -- When to Think, What to Compute, and How Much to Allocate