Research map / Large language models / Retrieval and knowledge
SegMem-RAG: Adaptive Memory for Retrieval-Augmented Generation in Open-Ended Knowledge Environments
Xuanbo Fan, Tianqi Zhao, Yi Cheng, Chi Xiu, Jiaxin Guo, Boci Peng, Bingjing Xu, Jessica Zhang, Feng Sun, Yan Zhang
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add Segment Planner (segment-wise reasoning) (ablation) | SEGMEM-RAG · PopQA | token-level F1: 37.6 -> 54.2 | Improved |
| add Segment Planner (segment-wise reasoning) (ablation) | SEGMEM-RAG · NQ | token-level F1: 45.4 -> 47.8 | Improved |
| add Feedback Evaluator (ablation) | SEGMEM-RAG · NQ | token-level F1: 43.2 -> 47.8 | Improved |
| add Feedback Evaluator (ablation) | SEGMEM-RAG · PopQA | token-level F1: 44.4 -> 54.2 | Improved |
| add Memory Controller (symbolic multi-level memory) (ablation) | SEGMEM-RAG · NQ | token-level F1: 31.7 -> 47.8 | Improved |
| add Memory Controller (symbolic multi-level memory) (ablation) | SEGMEM-RAG · PopQA | token-level F1: 32.3 -> 54.2 | Improved |
| add Coldstart Explorer (ablation) | SEGMEM-RAG · NQ | token-level F1: 43.3 -> 47.8 | Improved |
| add Coldstart Explorer (ablation) | SEGMEM-RAG · PopQA | token-level F1: 49.0 -> 54.2 | Improved |
| retrieve from all corpora (EnumRAG) instead of prompting without retrieval | Qwen2.5-7B-Instruct · Open-domain QA average | token-level F1: 30.1 -> 45.8 | Improved |
| random corpus selection (BlindRAG) instead of prompting without retrieval | Qwen2.5-7B-Instruct · Open-domain QA average | token-level F1: 30.1 -> 15.7 | Hurt |
| description-based corpus routing (ResLLM) instead of prompting without retrieval | Qwen2.5-7B-Instruct · Open-domain QA average | token-level F1: 30.1 -> 14.4 | Hurt |
| use SEGMEM-RAG instead of oracle exhaustive enumeration (EnumRAG) | Qwen2.5-7B-Instruct · Open-domain QA average | token-level F1: 45.8 -> 47.5 | Improved |
Closest papers by meaning
- Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection (ICLR 2024 · similarity 0.91)
- Long-Context LLMs Meet RAG: Overcoming Challenges for Long Inputs in RAG (ICLR 2025 · similarity 0.90)
- Adapting to Non-Stationary Environments: Multi-Armed Bandit Enhanced Retrieval-Augmented Generation on Knowledge Graphs (AAAI 2025 · similarity 0.90)
- Speculative RAG: Enhancing Retrieval Augmented Generation through Drafting (ICLR 2025 · similarity 0.90)
- RAG-DDR: Optimizing Retrieval-Augmented Generation Using Differentiable Data Rewards (ICLR 2025 · similarity 0.90)
- RAGRouter: Learning to Route Queries to Multiple Retrieval-Augmented Language Models (NeurIPS 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
