A Survey on Sequential Recommendation (Frontiers of Computer Science, 2025)

Overview

This post covers a survey on sequential recommendation published in *Frontiers of Computer Science* (November 2025).

• Title: A survey on sequential recommendation
• Venue: Frontiers of Computer Science, 2025 (published Nov 2025)
• Type: Survey
• Link: https://link.springer.com/article/10.1007/s11704-025-41329-w

Sequential recommendation treats a user's interaction history as an ordered sequence and predicts the next item of interest. Surveys in this area typically organize the literature by modeling paradigm, architecture components, training objectives, and evaluation protocols.

Background

Large-scale search, recommendation, and personalization systems face long-standing challenges in efficiency, scalability, and user intent understanding. Traditional pipeline approaches separate retrieval, ranking, and generation, which limits adaptability in the LLM era, where users expect natural language interaction, multi-hop reasoning, and up-to-date knowledge.

Taxonomy of Research Directions

| Dimension | Subcategories | Representative Ideas | Strengths | Limitations | |-----------|---------------|---------------------|-----------|-------------| | Modeling paradigm | Discriminative vs. generative retrieval | Two-tower, cross-encoder, DSI | Mature, scalable | Semantic drift, update cost | | LLM integration | RAG / Agent / Tool-use | Retrieval augmentation, search agents, API calls | Flexible, interpretable | Latency, error propagation | | Optimization objectives | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce annotations | | Evaluation | Offline / online / human | nDCG, MRR, LLM-as-judge, A/B testing | Comparable | Divergence from real satisfaction |

Evolution of the Field

• 2019–2021: BERT re-ranking and dense retrieval (DPR) establish neural foundations.
• 2022–2023: RAG and freshness-aware retrieval drive retrieval-generation fusion.
• 2024 onward: Conversational/agentic search and Gen-RecSys expand rapidly.
• 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth areas.

On the recommendation side, the field has progressed from matrix factorization and deep CTR models to sequential Transformers, LLM instruction following, and generative recommendation (Gen-Rec). The core tensions remain sparse user behavior, enormous item catalogs, and multi-objective business trade-offs.

Evaluation Paradigms

Typical benchmarks and metrics discussed in this literature:

• Datasets: MS MARCO, BEIR, Natural Questions, domain corpora, public recommendation datasets
• Metrics: nDCG@10, MRR, Recall@k, Hit@k, human preference, task success rate, latency, token cost
• Baselines: BM25, dense retrieval, cross-encoder re-ranking, retrieval-free LLMs, commercial search APIs

Concrete numerical results should be verified against the original paper's tables.

Key Insights

1. Architecture: Cascaded retrieval + re-ranking + generation remains mainstream, but agentic paradigms make retrieval strategy itself learnable. 2. Data: High-quality instruction data and click/session logs are both critical; synthetic data risks knowledge leakage and distribution shift. 3. Evaluation: The gap between offline metrics and online satisfaction is widening; LLM-as-judge should be cross-validated with human evaluation. 4. Deployment: Latency, cost, interpretability, and safety are hard industrial constraints—not just academic benchmark scores.

Engineering Checklist

| Check | Question | Suggestion | |-------|----------|------------| | Data | PII in training/index data? Version control? | Partitioned indexes, anonymization, rollback-capable embedding versions | | Latency | p99 budget? Retrieval steps? | Cascade + early stopping, hot-query caching, async re-ranking | | Quality | Does offline gain translate to online CTR/satisfaction? | Interleaving experiments, human audits, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelisting, adversarial detection, output filtering | | Cost | Token and GPU cost per query? | Small-model routing, distillation, hybrid sparse+dense retrieval |

Open Problems

• Lack of unified benchmarks; private data limits reproducibility
• Bias in LLM-based evaluation
• Safety and cost constraints for agentic systems on the open web
• Finer-grained process supervision, retrieval-reasoning co-training, multimodal and cross-lingual consistency, causal and fairness constraints in recommendation

Related Entries

• A Comprehensive Survey on Cross-Domain Recommendation
• A Comprehensive Survey on Retrieval Methods in Recommender Systems (arXiv:2407.21022)
• A Review of Modern Recommender Systems Using Generative Models (Gen-RecSys)
• A Survey of Generative Search and Recommendation in the Era of Large Language Models (arXiv:2404.16924)
• A Survey on LLM-powered Agents for Recommender Systems (arXiv:2502.10050)

Glossary

| Term | Meaning | |------|---------| | IR | Information Retrieval | | RAG | Retrieval-Augmented Generation | | LTR | Learning to Rank | | nDCG | Normalized Discounted Cumulative Gain | | Agentic Search | Modeling search as sequential decision-making and tool calling | | Gen-IR | Generative Information Retrieval |

> Note: This post is largely an editorial summary based on the paper's metadata and abstract. Quantitative claims should be verified against the original PDF at the Springer link above.