mlsanityData to 14 Oct 2026

ComRAG: Retrieval-Augmented Generation with Dynamic Vector Stores for Real-time Community Question Answering in Industry

arXiv 2506.21098 ↗First posted 26 Jun 2025cs.CL cs.AIcited by 3

On the map: Retrieval-augmented generation → Knowledge-graph and structured-knowledge RAG

Abstract (arXiv)

Community Question Answering (CQA) platforms can be deemed as important knowledge bases in community, but effectively leveraging historical interactions and domain knowledge in real-time remains a challenge. Existing methods often underutilize external knowledge, fail to incorporate dynamic historical QA context, or lack memory mechanisms suited for industrial deployment. We propose ComRAG, a retrieval-augmented generation framework for real-time industrial CQA that integrates static knowledge with dynamic historical QA pairs via a centroid-based memory mechanism designed for retrieval, generation, and efficient storage. Evaluated on three industrial CQA datasets, ComRAG consistently outperforms all baselines--achieving up to 25.9% improvement in vector similarity, reducing latency by 8.7% to 23.3%, and lowering chunk growth from 20.23% to 2.06% over iterations.

Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Placed in Knowledge-graph and structured-knowledge RAG, one of 15 directions in Retrieval-augmented generation. Builds on 9 of its 19 references that are in the map. First posted on arXiv 26 Jun 2025.

Builds on

9 of 19 references.

References · 9

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  3. 2019BERTScore: Evaluating Text Generation with BERTcited by 5,512
  4. 2020Dense Passage Retrieval for Open-Domain Question Answeringcited by 3,824
  5. 2023Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answeringcited by 41
  6. 2024ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Searchcited by 12
  7. 2024Reinforcement learning for question answering in programming domain using public community scoring as a human feedbackcited by 6
  8. 2023Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Modelscited by 3
  9. 2024Leveraging Topic Specificity and Social Relationships for Expert Finding in Community Question Answering Platformscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 1.

3 papers.

  1. 2025From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascadescited by 1
  2. 2025TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generationcited by 1
  3. 2026Enhancing Software Engineering Through Closed-Loop Memory Optimizationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025KERAG: Knowledge-Enhanced Retrieval-Augmented Generation for Advanced Question Answering
  2. 2024RAGONITE: Iterative Retrieval on Induced Databases and Verbalized RDF for Conversational QA over KGs with RAG
  3. 2025Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks
  4. 2024DuetRAG: Collaborative Retrieval-Augmented Generation
  5. 2026LakeQuest: A Three-Domain Benchmark for Grounded Question Answering across Data Lakes
  6. 2024LocalRQA: From Generating Data to Locally Training, Testing, and Deploying Retrieval-Augmented QA Systems
  7. 2026DynaRAG: Bridging Static and Dynamic Knowledge in Retrieval-Augmented Generation
  8. 2025From Search to Reasoning: A Five-Level RAG Capability Framework for Enterprise Data