Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
0 results for “long-term memory”
MobileMem: Learning from a Year of Mobile Experiences
MobileMem is a new AI benchmark and framework for on-device long-term memory, built from a year-scale dataset of mobile user experiences to enable agents that remember, understand, and adapt across time.
Aug 17, 2026
Controlled Memory Interference in Continual LLM Agents
Researchers introduce Controlled Memory Interference (CMI), a diagnostic and data-generation framework to study how long-term memory in continual LLM agents evolves under competing memory relationships — revealing that interference, not just scale, critically impacts update plasticity and stability.
Aug 11, 2026
We're building agents that can read millions of documents, but still forget a video they watched yesterday.
A developer identifies a gap in AI agent memory architecture—specifically the lack of persistent, reusable understanding from video inputs—and releases an open-source tool to build local indexes for video-derived multimodal data.
Published Jul 6, 2026 · Analyzed Jul 8, 2026