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

arXiv: https://arxiv.org/abs/2506.21098 · HTML: https://mlsanity.com/paper/2506.21098/

## 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.

## Placed in

- Retrieval-augmented generation / [Knowledge-graph and structured-knowledge RAG](https://mlsanity.com/rag/knowledge-graph-and-structured-knowledge-rag/)

## Builds on (most cited first, 9 of 9)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Dense Passage Retrieval for Open-Domain Question Answering](https://mlsanity.com/paper/2004.04906/) (2020)
- [Empower Large Language Model to Perform Better on Industrial Domain-Specific Question Answering](https://mlsanity.com/paper/2305.11541/) (2023)
- [ProCQA: A Large-scale Community-based Programming Question Answering Dataset for Code Search](https://mlsanity.com/paper/2403.16702/) (2024)
- [Reinforcement learning for question answering in programming domain using public community scoring as a human feedback](https://mlsanity.com/paper/2401.10882/) (2024)
- [Enhancing Answer Selection in Community Question Answering with Pre-trained and Large Language Models](https://mlsanity.com/paper/2311.17502/) (2023)
- [Leveraging Topic Specificity and Social Relationships for Expert Finding in Community Question Answering Platforms](https://mlsanity.com/paper/2407.04018/) (2024)

## Built on by (most cited first, 3 of 3)

- [From Deferral to Learning: Online In-Context Knowledge Distillation for LLM Cascades](https://mlsanity.com/paper/2509.22984/) (2025)
- [TagRAG: Tag-guided Hierarchical Knowledge Graph Retrieval-Augmented Generation](https://mlsanity.com/paper/2601.05254/) (2025)
- [Enhancing Software Engineering Through Closed-Loop Memory Optimization](https://mlsanity.com/paper/2606.05646/) (2026)

## 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.