AI Paper Atlas

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

AAAI 2026 · Large language models › Retrieval and knowledge · approach: RAG robustness and evaluation

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 changedWhereMeasuredEffect
add Segment Planner (segment-wise reasoning) (ablation)SEGMEM-RAG · PopQAtoken-level F1: 37.6 -> 54.2Improved
add Segment Planner (segment-wise reasoning) (ablation)SEGMEM-RAG · NQtoken-level F1: 45.4 -> 47.8Improved
add Feedback Evaluator (ablation)SEGMEM-RAG · NQtoken-level F1: 43.2 -> 47.8Improved
add Feedback Evaluator (ablation)SEGMEM-RAG · PopQAtoken-level F1: 44.4 -> 54.2Improved
add Memory Controller (symbolic multi-level memory) (ablation)SEGMEM-RAG · NQtoken-level F1: 31.7 -> 47.8Improved
add Memory Controller (symbolic multi-level memory) (ablation)SEGMEM-RAG · PopQAtoken-level F1: 32.3 -> 54.2Improved
add Coldstart Explorer (ablation)SEGMEM-RAG · NQtoken-level F1: 43.3 -> 47.8Improved
add Coldstart Explorer (ablation)SEGMEM-RAG · PopQAtoken-level F1: 49.0 -> 54.2Improved
retrieve from all corpora (EnumRAG) instead of prompting without retrievalQwen2.5-7B-Instruct · Open-domain QA averagetoken-level F1: 30.1 -> 45.8Improved
random corpus selection (BlindRAG) instead of prompting without retrievalQwen2.5-7B-Instruct · Open-domain QA averagetoken-level F1: 30.1 -> 15.7Hurt
description-based corpus routing (ResLLM) instead of prompting without retrievalQwen2.5-7B-Instruct · Open-domain QA averagetoken-level F1: 30.1 -> 14.4Hurt
use SEGMEM-RAG instead of oracle exhaustive enumeration (EnumRAG)Qwen2.5-7B-Instruct · Open-domain QA averagetoken-level F1: 45.8 -> 47.5Improved

Closest papers by meaning

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy