A Survey of LLM-Empowered Agents for Recommendation and Search: Towards Next-Generation Information Retrieval
Source: arXiv:2503.05659 (March 2025) Authors: Yu Zhang, Shutong Qiao, Jiaqi Zhang, Tzu-Heng Lin, Chen Gao, Yong Li Type: Survey
Key Points
- Provides a unified perspective on LLM-empowered agents for recommendation and search, organizing scattered work into a comparable framework.
- Decomposes method components: representation learning, retrievers, rerankers, planners, generators, and feedback mechanisms, easing engineering adoption.
- Discusses interfaces with LLM tool calling, reinforcement learning, and multi-agent collaboration, outlining paths from research prototypes to industrial systems.
- Lists open problems: evaluation credibility, latency and cost, hallucination and safety, cross-lingual and multimodal extension.
- Dense retrieval: high recall, low latency, suited to first-stage retrieval.
- Late interaction (e.g., ColBERT): higher accuracy but larger index footprint.
- Generative IR: directly "generates" documents as tokens or docids, simplifying cascades.
- Agentic search: models search as sequential decision-making, supporting multi-hop reasoning and self-reflection.
- 2019–2021: BERT reranking and DPR establish neural retrieval foundations.
- 2022–2023: RAG and FreshLLM drive retrieval-generation fusion.
- 2024 onward: conversational/agentic search and Gen-RecSys explode.
- 2025–2026: RL-trained search agents, Deep Research, and GraphRAG become new growth frontiers.
- 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 and token cost.
- Baselines: BM25, dense retrieval, cross-encoder reranking, retrieval-free LLMs, commercial search APIs.
- Lack of unified benchmarks; private data irreproducibility; LLM evaluation bias; safety and cost constraints for agentic systems.
- Future work: finer-grained process supervision, joint retrieval–reasoning training, enterprise metadata governance, multimodal and cross-lingual consistency, test-time compute allocation, deeper integration with knowledge graphs, and causal/fairness constraints for recommendation.
- A Comprehensive Survey on Reinforcement Learning-based Agentic Search
- A Survey of Conversational Search (Oct 2024)
- A Survey of Model Architectures in Information Retrieval (Jan 2025)
- A Survey on Knowledge-Oriented Retrieval-Augmented Generation (Mar 2025)
Taxonomy
| Dimension | Subclass | Representative Approaches | Strengths | Limitations | |-----------|----------|---------------------------|-----------|-------------| | Modeling paradigm | Discriminative / generative retrieval | Bi-encoders, cross-encoders, 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 goals | Relevance / diversity / freshness | Multi-objective LTR, RLHF, online learning | Business-aligned | Scarce annotations | | Evaluation | Offline / Online / Human | nDCG, MRR, LLM-as-judge, A/B tests | Comparable | Deviates from real satisfaction |
Four Main Research Lines
Timeline of Evolution
Evaluation Paradigm
Insights for Search, Recommendation, and Personalization
1. Architecture: cascaded retrieve–rerank–generate remains mainstream, but the agentic paradigm makes retrieval count and strategy themselves learnable. 2. Data: high-quality instruction data and click/session logs matter equally; synthetic data needs safeguards against leakage and distribution shift. 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge requires cross-validation with human evaluation. 4. Product: latency, cost, interpretability, and safety are hard constraints for industrial deployment.
Open Problems and Future Directions
Engineering Checklist
| Item | Question | Recommendation | |------|----------|----------------| | Data | PII in training/index? Version management? | Partitioned indexes, anonymization, rollback-capable embeddings | | Latency | p99 budget? Number of retrieval steps? | Cascades + early stopping, hot-query caching, async reranking | | Quality | Do offline gains transfer to online CTR/satisfaction? | Interleaving experiments, human audits, citation verification | | Safety | Poisoning/bias from open retrieval? | Source whitelists, adversarial detection, output filtering | | Cost | Per-query tokens and GPU usage? | Small-model routing, distillation, hybrid sparse+dense |