AURA-Mem proposes a constant-size recurrent memory for robot policies that writes only when an observation would change the next action, drastically reducing memory writes while maintaining accuracy. It uses a learned gate trained on action-error signal, achieving fixed 4,224-byte inference state vs growing KV-cache. Experiments show matching success rates with up to 7x fewer writes.

Weaviate announces the general availability of Engram, a managed memory and context service for agentic applications. It addresses long-context degradation, messy raw data, and multi-agent context fragmentation through asynchronous pipelines, templates, and built-in scopes, helping agents compound value over time.

Reachy Mini can now use remote tools hosted in Hugging Face Spaces via MCP, allowing it to check weather or search the web with a single command. The article covers built-in tools, profile-based control, tool installation, naming conventions, and current limitations.

Microsoft announced two new text LLMs: MAI-Thinking-1 (35B parameters, reasoning) and MAI-Code-1-Flash (5B parameters, code). Both are trained on clean, licensed data without distillation, with MAI-Thinking-1 claiming preference over Sonnet 4.6. MAI-Code-1-Flash is rolling out to GitHub Copilot users in VS Code.

Accelerated computing has revolutionized industrial engineering, compressing simulation times from weeks to hours. Today’s remaining challenges sit in the end-to-end workflow surrounding the simulations: computer-aided design, meshing, simulation setup and debugging, as well as post-processing and generating summary reports of these processes. At GTC Taipei at COMPUTEX, NVIDIA and more than a dozen engineering software providers are showcasing how autonomous AI agents automate this entire workflow. These AI engineers are based on NVIDIA NemoClaw, an open blueprint for building specialized, long-running agents with a secure runtime and frontier models.