New frameworks and protocols (CORVUS, MCP stateless, EvoLib, Echoverse) are advancing the development of AI agents capable of memory, tool use, and autonomous action, while the hype around some agents fades, signaling a maturing but critical field.
After weeks of viral content, street queues in China, and an enterprise move by Nvidia, the buzz around Openclaw has evaporated. The silence isn't a mystery but a symptom of the clash between the promise of magical automation and the technical realit...
Microsoft Research unveils Echoverse, twelve faithful, verifiable synthetic worlds for training computer-use agents. A 9B model nearly doubles its score, closing in on GPT-5.4. For those running LLMs on-premise and handling sensitive data, the implic...
Microsoft Research introduces EvoLib, a framework that transforms inference-time experience into reusable, evolving knowledge without model updates. We analyze its implications for on-premise deployment and data sovereignty.
The Model Context Protocol drops session state, freeing requests from individual server instances. A leap forward for horizontal scaling of tool-using AI, with direct consequences for on-premise deployments, data control, and operational costs.
A reusable template, llm-wiki-memory-template, lets LLM agents persistently accumulate knowledge, deliberately preserving failed attempts. Three case studies show how this architecture can solve the structural loss of negative results in research and...
CORVUS is a new trajectory architecture for LLM-based coding agents that decouples file-read actions from their snapshots, maintaining a synchronized file registry. This eliminates redundant copies and stale data, reducing input tokens by up to 50% a...
