AI Paper Atlas

Research map / Large language models / Retrieval and knowledge

From Single to Multi-Granularity: Toward Long-Term Memory Association and Selection of Conversational Agents

Derong Xu, Yi Wen, Pengyue Jia, Yingyi Zhang, Wenlin Zhang, Yichao Wang, Huifeng Guo, Ruiming Tang, Xiangyu Zhao, Enhong Chen, Tong Xu

ICLR 2026 · Large language models › Retrieval and knowledge · approach: Long-context and personalized retrieval · 42 citations (OpenAlex)

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 Gaussian-mixture memory association (ablation)MemGAS · LongMemEval-sGPT4o-J: 57.20 -> 60.20Improved
add Personalized PageRank retrieval over the association graph (ablation)MemGAS · LongMemEval-sGPT4o-J: 56.60 -> 60.20Improved
add entropy-based granularity router (ablation)MemGAS · LongMemEval-sF1: 18.88 -> 20.38Improved
add memory association (GMM + PPR) (ablation)MemGAS · LongMemEval-sRecall@3: 74.89 -> 78.51Improved
enable all four modules together vs none (ablation)MemGAS · LongMemEval-sF1: 13.78 -> 20.38Improved
use router and association instead of naive combination of granularities (ablation)multi-granularity retrieval · LongMemEval-sF1: 14.59 -> 20.38Improved
use multiple granularities (naive combination) instead of session-level only (ablation)Contriever retrieval · LongMemEval-sF1: 13.78 -> 14.59Improved
retrieve with summary-level or keyword-level units only (ablation)Contriever retrieval · LongMemEval-sGPT4o-J: 55.40 -> 28.80Hurt
retrieve with turn-level units instead of session-level (ablation)Contriever retrieval · LongMemEval-sGPT4o-J: 55.40 -> 57.60Improved
increase retrieved Top-K to high values (ablation)MemGAS · LongMemEval-sF1Hurt
use MemGAS instead of full history contextGPT-4o-mini QA · LongMemEval-sGPT4o-J: 50.60 -> 60.20Improved
MemGAS vs HippoRAG 2 on LoCoMo GPT4o-JMemGAS · LoCoMoGPT4o-J: 45.62 -> 41.07Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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