REVIEW 28 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
Think Before Recommend: Unleashing the Latent Reasoning Power for Sequential Recommendation
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 28 Pith papers
-
Beyond Matching: Category-Guided Latent Intent Reasoning for Generative Retrieval in E-Commerce
CaLIR learns continuous latent intent states guided by product category hierarchies for generative retrieval, combining hierarchical reasoning and dynamic prefix tries to balance effectiveness and low-latency inferenc...
-
Post Reasoning: Improving the Performance of Non-Thinking Models at No Cost
Post-Reasoning boosts LLM accuracy by reversing the usual answer-after-reasoning order, delivering mean relative gains of 17.37% across 117 model-benchmark pairs with zero extra cost.
-
LoopCTR: Unlocking the Loop Scaling Power for Click-Through Rate Prediction
LoopCTR trains CTR models with recursive layer reuse and process supervision so that zero-loop inference outperforms baselines on public and industrial datasets.
-
BEAR: Towards Beam-Search-Aware Optimization for Recommendation with Large Language Models
BEAR adds a beam-search-aware regularization to LLM fine-tuning for recommendations that forces positive-item tokens to rank in the top-B candidates at each decoding step to avoid premature pruning.
-
S$^2$GR: Stepwise Semantic-Guided Reasoning in Latent Space for Generative Recommendation
S²GR adds stepwise thinking tokens with contrastive supervision on codebook clusters to balance computational focus and ground reasoning paths in generative recommendation.
-
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
A lightweight recursive model with an evidence-anchored correction gate refines persistent user preference states and matches or outperforms larger sequential and LLM recommenders on three benchmarks.
-
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.
-
DREAM: Dynamic Refinement of Early Assignment Mappings
DREAM proposes intent-aware tokenization, frozen-model evaluation, and dynamic beams to refine early SID assignments and improve cold-start performance in generative recommenders on Amazon benchmarks.
-
When Does Latent Reasoning Help? MeRa: Metric-Space Bias for Spatial Prediction
MeRa adds metric-space bias to latent reasoning, turning potential degradation into gains for spatial prediction and achieving best NDCG@10 on three benchmarks.
-
SAPO: Step-Aligned Policy Optimization for Reasoning-Based Generative Recommendation
SAPO computes per-reasoning-step group-relative advantages in RL to improve credit assignment for structured generation of semantic identifiers in recommendation systems.
-
Factorized Latent Reasoning for LLM-based Recommendation
FLR factorizes latent reasoning into multiple preference factors using multi-factor attention and regularizations, outperforming baselines on recommendation benchmarks while adding robustness and interpretability.
-
ClusterRAG: Cluster-Based Collaborative Filtering for Personalized Retrieval-Augmented Generation
ClusterRAG applies density-based clustering to user profiles for collaborative retrieval in personalized RAG and reports best performance on LaMP tasks by combining target and similar-user profiles.
-
SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling
Speculative precomputation of foundation-model user–item embeddings decouples heavy inference from the serving path and yields 0.67% revenue gain at Meta ads scale.
-
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.
-
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.
-
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%.
-
A Survey on Generative Recommendation: Data, Model, and Tasks
This survey organizes generative recommendation into data, model, and task dimensions, identifying five advantages including world knowledge integration and creative generation while noting challenges in benchmarks an...
-
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.
-
RecRec: Recursive Refinement for Sequential Recommendation
A lightweight recursive latent-state recommender with an evidence-anchored correction gate matches or exceeds larger SOTA sequential recommenders on three benchmarks.
-
SSRLive: Live Streaming Recommendation with Dynamic Semantic ID
SSRLive combines generative and discriminative modules with dynamic semantic IDs to improve live streaming recommendations, reporting gains of +3.38% watch time, +0.72% GMV, +3.12% follower growth, and +2.92% interact...
-
VirtualMLE: A Virtual ML Engineer that Optimizes Sequential Recommenders
VirtualMLE deploys an LLM agent with execution-reflection-memory to tune sequential recommenders, reaching competitive quality on Amazon benchmarks with fewer trials and transferring heuristics across datasets.
-
Generative Spatiotemporal Intent Sequence Recommendation via Implicit Reasoning in Amap
GPlan compresses LLM reasoning into small models via Progressive Implicit CoT Distillation and Spatiotemporal Counterfactual DPO to generate logically coherent and physically executable intent sequences for recommendation.
-
SOLARIS: Speculative Offloading of Latent-bAsed Representation for Inference Scaling
SOLARIS speculatively precomputes user-item latent representations to decouple large-model inference from real-time serving, delivering 0.67% revenue gain when deployed in Meta's ad system.
-
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.
-
Stop Overthinking: A Survey on Efficient Reasoning for Large Language Models
A survey organizing techniques to achieve efficient reasoning in LLMs by shortening chain-of-thought outputs.
-
The Case Against Generation for Retrieval: Discriminative Language Models as Effective Retrievers
A shared-encoder two-tower retriever built from a 0.6B LLM matches or beats an 8B generative recommender on Recall@10 across three Amazon datasets.
discussion (0)
Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.