memory — AI Digest

8 мая Anthropic Launches Claude Managed Agents: Dreams, Outcomes, Multiagent Orchestration Anthropic tools
6 июн OpenAI Launches Dreaming V3: Background Memory Synthesis for ChatGPT with 5x Compute Reduction OpenAI tools
26 июн Yandex Releases Major Alice AI Update: Cross-Session Memory, Personalization, and Live Accessibility Mode Yandex models-llm
31 июл Metis: Memory Foundation Model MemTensor research
15 авг Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence Zhejiang University research
16 мая MemLens: Benchmark for Multimodal Long-Term Memory in Vision-Language Models NVIDIA research
4 июн Echo-Infinity: Real-Time Infinite Video Generation via Learnable Memory Query research
14 июн EvoArena: LLM Agents Score Only 40% on Dynamic Evolving Environments MIT / NUS / Salesforce research
14 июл ABot-AgentOS: General Robotic Agent OS with Lifelong Multi-modal Memory Alibaba research
2 авг Metis: Memory Foundation Model MemTensor, Renmin University, NUS, Shanghai Jiao Tong University, Tongji University research
3 июн Do Language Models Need Sleep? Offline Recurrence as Memory Consolidation for Improved Inference Google / CMU research
12 июн EvoArena: LLM Agents Score Only 39.6% on Dynamic Evolving Environments Benchmark MIT research
25 июн Are We Ready For an Agent-Native Memory System? SJTU Benchmarks 12 Architectures research
16 мая GitHub Copilot: Grok Code Fast 1 Deprecated, User Memory Preferences for Pro GitHub tools
9 июн Echo-Memory: Controlled Study of Memory Mechanisms in Action-Conditioned Video World Models Microsoft Research research
16 июн Memory is Reconstructed, Not Retrieved: Graph Memory Improves LLM Agent Recall by 23% National University of Singapore research
14 июл LightMem-Ego: Lightweight Streaming Multimodal Memory for Smartphones and AI Glasses ZJUNLP research
16 июл KnowAct-GUIClaw: Self-Evolving Memory and Skill Library for Cross-Platform GUI Agents Harbin Institute of Technology research
14 авг LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation research
19 авг IBM Research benchmarks how much agentic memory each model tier actually needs IBM Research research