REVIEW 11 cited by
Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Sequential Recommendation (SeqRec) aims to predict the next item by capturing sequential patterns from users' historical interactions, playing a crucial role in many real-world recommender systems. However, existing approaches predominantly adopt a direct forward computation paradigm, where the final hidden state of the sequence encoder serves as the user representation. We argue that this inference paradigm, due to its limited computational depth, struggles to model the complex evolving nature of user preferences and lacks a nuanced understanding of long-tail items, leading to suboptimal performance. To address this issue, we propose \textbf{ReaRec}, the first inference-time computing framework for recommender systems, which enhances user representations through implicit multi-step reasoning. Specifically, ReaRec autoregressively feeds the sequence's last hidden state into the sequential recommender while incorporating special reasoning position embeddings to decouple the original item encoding space from the multi-step reasoning space. Moreover, we introduce two lightweight reasoning-based learning methods, Ensemble Reasoning Learning (ERL) and Progressive Reasoning Learning (PRL), to further effectively exploit ReaRec's reasoning potential. Extensive experiments on five public real-world datasets and different SeqRec architectures demonstrate the generality and effectiveness of our proposed ReaRec. Remarkably, post-hoc analyses reveal that ReaRec significantly elevates the performance ceiling of multiple sequential recommendation backbones by approximately 30\%-50\%. Thus, we believe this work can open a new and promising avenue for future research in inference-time computing for sequential recommendation.
Forward citations
Cited by 11 Pith papers
-
BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
BEAR is a cheap token-level top-B regularizer for LLM-based recommendation, but its central claim that this condition is necessary for beam-search survival is incorrect.
-
Grevo: A Unified Generative Recommendation Framework with Evolutionary Item Indexing
Grevo lets a generative recommender evolve item identifier codes through budgeted posterior-guided search instead of training a separate tokenizer.
-
RecRec: Recursive Refinement for Sequential Recommendation
Recursive latent-state refinement with an evidence-anchored correction gate matches or beats much larger sequential, graph, and LLM recommenders on three benchmark datasets.
-
Uncertainty-aware Generative Recommendation
UGR injects uncertainty into generative recommendation preference optimization via confidence-weighted rewards, difficulty-aware reweighting, and explicit confidence tokens, improving ranking accuracy and training stability.
-
Think When Needed: Model-Aware Reasoning Routing for LLM-based Ranking
A per-instance router trained to predict the utility gain of reasoning decides when an LLM should think before ranking, improving NDCG by up to 6.3% while cutting generation tokens by up to 75%.
-
The Case Against Generation for Retrieval: Discriminative Language Models as Effective Retrievers
LLM-native two-tower retrieval with EOS pooling, cross-dataset transfer, distillation from a cross-encoder, and latent user reasoning reaches SoTA-comparable recall on Amazon benchmarks.
-
The Latent Space: Foundation, Evolution, Mechanism, Ability, and Outlook
A large survey organizes latent-space work in language-based models by foundation, evolution, four mechanisms, seven abilities, and open challenges.
-
Why Thinking Hurts: Diagnosing and Rectifying Linguistic Inertia in Large Language Models for Recommendation
Chain-of-thought reasoning degrades semantic-ID recommendation accuracy through 'linguistic inertia,' and a training-free compression-plus-contrastive decoding fix restores and often improves accuracy.
-
Implicit Reasoning in Large Language Models: A Comprehensive Survey
A survey organizing implicit (silent) reasoning in LLMs into three execution paradigms, plus evidence, benchmarks, and challenges.
-
Bridging Search and Recommendation through Latent Cross Reasoning
A latent cross reasoning model with contrastive learning and GRPO reinforcement learning improves search-enhanced recommendation on Qilin and KuaiSAR.
-
Act-With-Think: Chunk Auto-Regressive Modeling for Generative Recommendation
CAR predicts each item as a chunk of semantic IDs plus a unique ID in one autoregressive step and reports large Recall@5 gains on three Amazon datasets.
Discussion (0). Sign in to comment.