RecSys: ACM Conference on Recommender Systems - Overview and Context

Forum topic · 小凯 · 2026-07-05

Summary

RecSys is the ACM Conference on Recommender Systems, the premier venue for research on recommendation systems and personalization. This forum post situates RecSys within the broader search and recommendation ecosystem, covering how large language models (LLMs) are reshaping the classic pipeline of retrieval, ranking, and generation. It outlines the conference's thematic scope: open-domain information access, conversational search, semantic understanding in recommendation, and end-to-end architectures combining external knowledge sources with generative models. Key topics include representation learning, retrievers, re-rankers, planners, and feedback mechanisms, alongside emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration. The post highlights open problems including evaluation reliability, latency and cost constraints, hallucination and safety, and cross-lingual/multimodal extension. It also provides practical engineering guidance: cascaded retrieval with early stopping, hybrid sparse-dense retrieval, LLM-as-judge evaluation cross-validated with human assessment, and production constraints around latency, cost, interpretability, and safety. Official site: https://recsys.acm.org/.

RecSys: ACM Conference on Recommender Systems

Official site: https://recsys.acm.org/

Resource type: Conference / Workshop

RecSys is the flagship ACM conference dedicated to recommender systems, covering foundational and applied research in recommendation, personalization, and user intent understanding.

Background and Scope

In large-scale search, recommendation, and personalization systems, recommendation research has long faced challenges around efficiency, scalability, and user intent understanding. Traditional pipeline-style approaches often treat retrieval, ranking, and generation as disconnected stages, which struggles to meet the demands of the LLM era: natural language interaction, multi-hop reasoning, and real-time knowledge.

Core topics in scope include:

Open-domain information access and enterprise knowledge retrieval
Conversational search and semantic understanding in recommendation
End-to-end architectures that coordinate external knowledge sources with generative models

Key Themes and Contributions

A unified perspective that organizes scattered related work into a comparable framework
Clear decomposition of method components: representation learning, retrievers, re-rankers, planners, generators, and feedback mechanisms
Reproducible benchmarks, datasets, and taxonomy tables that lower entry barriers for future researchers
Interfaces with emerging paradigms such as LLM tool calling, reinforcement learning, and multi-agent collaboration, including migration paths from research prototypes to industrial systems
Open problems: evaluation trustworthiness, latency and cost, hallucination and safety, and cross-lingual/multimodal extension

Typical Technical Pipeline

1. Input and representation: encode queries, documents, and user context into dense or sparse representations, or structured prompts 2. Core modules: retrievers, re-rankers, planners, memory modules, and tool interfaces, chained or parallelized per task 3. Learning strategies: supervised fine-tuning, contrastive learning, distillation, reinforcement learning (including process rewards), and bootstrap data synthesis 4. Inference strategies: single-round retrieval, iterative retrieval, parallel sub-queries, early stopping, and budget control

Insights for Search, Recommendation, and Personalization

1. Architecture: cascaded retrieval + re-ranking + generation remains mainstream, but agentic paradigms are making "how many retrievals and what policy" itself a learnable object 2. Data: high-quality instruction data and click/session logs are equally critical; synthetic data must guard against knowledge leakage and distribution shift 3. Evaluation: the gap between offline metrics and online satisfaction is widening; LLM-as-judge needs cross-validation with human assessment 4. Product: latency, cost, explainability, and safety policies are hard constraints for industrial deployment — academic benchmarks alone are not enough

Engineering Checklist

| Item | Question | Recommendation | |------|----------|----------------| | Data | Does training/index contain PII? How are versions managed? | Partitioned indexes, sanitization, rollback-able embedding versions | | Latency | What is the p99 budget? How many retrieval steps? | Cascade + early stopping, cache hot queries, async re-ranking | | Quality | Do offline gains translate to online CTR/satisfaction? | Interleaving experiments, human audits, citation verification | | Safety | Does open retrieval introduce poisoning/bias? | Source whitelists, adversarial detection, output filtering | | Cost | Per-query token and GPU usage? | Small-model routing, distillation, sparse+dense hybrid retrieval |

Glossary

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

Related Entries

2025 SIGIR Workshop on eCommerce
CIKM 2024 Workshop on Multimodal Search and Recommendations
EACL 2024 Workshop on Personalization of Generative AI Systems
ICDM MMSR 2025

> Readers are advised to treat paper conclusions as directional evidence, validating via small-scale shadow experiments and A/B testing before full production rollout.