# AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval

Source: [AssoMem: Scalable Memory QA with Multi-Signal Associative Retrieval](<https://www.sota2.com/research/paper/68fa7c0a1e209131cea8c059>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T05:55:15.118Z

Authors: Kai Zhang, Xinyuan Zhang, Ejaz Ahmed, Hongda Jiang, Caleb Kumar, Kai Sun, Zhaojiang Lin, Sanat Sharma, Shereen Oraby, Aaron Colak, Ahmed Aly, Anuj Kumar, Xiaozhong Liu, Xin Luna Dong

Published: 2025-10-12T01:23:23.000Z

## Abstract

Accurate recall from large scale memories remains a core challenge for memory augmented AI assistants performing question answering (QA), especially in similarity dense scenarios where existing methods mainly rely on semantic distance to the query for retrieval. Inspired by how humans link information associatively, we propose AssoMem, a novel framework constructing an associative memory graph that anchors dialogue utterances to automatically extracted clues. This structure provides a rich organizational view of the conversational context and facilitates importance aware ranking. Further, AssoMem integrates multi-dimensional retrieval signals-relevance, importance, and temporal alignment using an adaptive mutual information (MI) driven fusion strategy. Extensive experiments across three benchmarks and a newly introduced dataset, MeetingQA, demonstrate that AssoMem consistently outperforms SOTA baselines, verifying its superiority in context-aware memory recall.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2510.10397>)

[PDF](<https://arxiv.org/pdf/2510.10397.pdf>)
