44 stories tagged Memory
Recall is an open-source memory system for AI agents that automatically updates its knowledge when facts change. It aims to make AI more reliable by ensuring it works with the most current information.
Belgian startup Corbenic AI has launched Galahad, a new AI memory system that claims to cut energy use by 93% while enhancing security. This could make AI systems more sustainable and cost-effective for everyday users.
Researchers from the University of Washington and Carnegie Mellon University released CapMem, a benchmark with 75 videos and 1,000 questions to test whether AI can use textual captions as episodic memory for long-duration wearable camera footage.
A new benchmark called MERIT measures the marginal utility of long-term memory for tool-using LLM agents. The study finds that memory often fails to improve task performance, especially when access costs are high, challenging assumptions about AI memory in real-world applications.
A new study on Qwen3 models reveals a 'Memory Trust Gap' where AI agents with persistent memory increasingly trust outdated stored facts over current authoritative evidence as model capability grows.
Researchers released SSAKG 2.0, an open-source software package that builds Structural Sequential Associative Knowledge Graphs (SSAKGs) to store and retrieve ordered sequences. The new version introduces bit-level algorithms that efficiently search graph connections, enabling the reconstruction of complete sequences from partial, unordered inputs.
Google is imposing new memory restrictions on Android apps due to AI-driven hardware shortages. This could impact lower-cost phones, forcing developers to optimize their apps for smaller memory budgets.
Callosium is an open-source project that allows multiple AI models to share a single memory system stored in plain Markdown files. This could make AI interactions more consistent and context-aware across different platforms.
Stanford researchers introduced AgentKVShift, a training-free technique that reduces the cost of AI memory systems by up to 90% by reusing key-value (KV) caches for structured memory units like summaries and tags, making AI agents significantly more efficient.
Cognikernel is a new open-source tool that gives AI coding assistants like Claude Code and Codex persistent local memory. It automatically captures architectural decisions and project context during coding sessions, eliminating the need for manual markdown files.
India's smartphone market is shrinking as the AI boom drives up demand for memory chips, raising prices and forcing Apple, Samsung, and others to rethink their strategies. Consumers may soon see fewer high-end features in affordable phones.
Researchers have developed a new system called Oracle Agent Memory to help AI assistants remember important details over long conversations. This could make AI tools more reliable for tasks that span multiple sessions, like complex projects or ongoing customer support.
A new paper explores integrating memory into every step of an AI agent's reasoning loop, but warns this approach could inflate latency by up to 83x. The work highlights a tension between memory-rich reasoning and real-time performance.
ContextCore is an open-source project that enables AI agents to remember long conversations on Apple Silicon devices using GPU-accelerated context retrieval, making on-device AI far more practical for complex, multi-turn tasks.
Context Warp Drive is an open-source tool that helps AI agents remember important information over long conversations. It could make AI assistants much more reliable for complex tasks.
AI agents can develop shared languages through interaction, and the way they store memories significantly impacts their success. This discovery could improve how AI systems communicate and collaborate in the future.
Researchers introduced ContextForge, a system that helps large language models maintain relevant information across long conversations by recycling context instead of replaying entire histories. This could slash token usage and improve multiturn reasoning.
AI memory benchmarks often hide key details, making it hard to compare models fairly. This lack of transparency affects how we evaluate AI capabilities.
Researchers introduced MemTrace, a new benchmark that evaluates AI long-term memory by tracking individual knowledge points across three controlled dimensions, rather than aggregating accuracy over independent question rows.
Researchers have identified memory traces in AI models that behave similarly to biological memory units in human brains. This discovery could help us understand how AI learns and remembers, potentially improving future AI systems.
Researchers created Poker Arena, a Texas Hold'em platform to test AI's strategic reasoning and memory. It evaluates nine different cognitive skills, offering deeper insights than traditional benchmarks.
A new research paper argues that AI needs explicit memory to reach human-like intelligence. This could change how we build and interact with AI in the future.
New research shows that adding memory to AI models can actually make them perform worse and more likely to agree with harmful ideas. This challenges the assumption that memory always improves AI.
Researchers developed a new memory system called Engram that improves AI accuracy by focusing on relevant information rather than full history. This could make AI assistants faster and more precise in their responses.