VoiceMem: dual-brain memory brings near-zero latency long-term recall to voice agents
青稞AI · wechat · 2026-09-07
Researchers from NTU, Tsinghua, CUHK and others (first author Zhifei Xie, corresponding author Shuicheng Yan) released VoiceMem, a long-term memory framework for real-time voice agents. It pairs an informational 'left brain' (Schema-Entity indexing with cluster emergence) with an emotional 'right brain' (persona and affect attribution), and streams retrieval across four stages so the 134ms dual-brain search fits inside the VAD window for near-zero added latency. On LoCoMo it scores 91.2 retrieving only 5 memories, beating Mem0's top-200 by 30 points, and leads on 11 of 14 capability categories in its new ChatMem-Bench. Framework, dataset and demo are open source, with Qwen Audio Agent integration.
Related event: VoiceMem Cuts Voice AI Memory Retrieval Latency to 134ms(2 posts)→
More from Research
- Interpretability credit debate points back to Doshi-Velez & Kim's foundational 2017 paper — StephenLCasper · 2026-09-07
- Dev open-sources a dependency-free LLM eval harness that catches regressions, not averages — zahidsaim23 · 2026-09-07
- Simulated fruit fly brain gets to "play" Bad Apple in viral demo — SALM0N_SLD · 2026-09-07
- Ant's LLaDA-Image Goes Open Source: 90% Text-Free Pretraining Tops Open-Source T2I Charts — 机器之心 · 2026-09-07
- Aging researcher calls new AI clinical-trials paper 'most important of my life', unveils it in Paris — AllThingsApx · 2026-09-07
- Quantum Money: The 5,000-Year Endgame of Cash, Forging and Sovereignty — StefanoGogioso · 2026-09-07