AI Agents
AI Agent technology and applications
Articles
NVIDIA AI Introduces SpatialClaw: A Training-Free Agent That⭐8
NVIDIA AI launches SpatialClaw, a training-free agent using code as an action interface for spatial reasoning tasks without environment-specific training.
Salesforce CodeGen Tutorial: Generate, Validate, and Rerank⭐8
Implement Salesforce CodeGen for Python code generation with safety checks, unit-test validation, and candidate reranking in a complete end-to-end pipeline.
Perplexity Launches Brain: A Self-Improving Memory System That⭐8
Perplexity launches Brain, a self-improving context graph memory system for AI agents that learns and optimizes overnight without human input.
OpenAI Releases LifeSciBench: A 750-Task Benchmark for⭐6
OpenAI’s LifeSciBench is a 750-task benchmark evaluating AI on real-life science research with expert rubrics, where even top models pass only ~1 in 3 tasks.
NVIDIA SkillSpector Guide: Scanning AI Skills for Security Risks⭐7
Learn how to use NVIDIA SkillSpector for AI skill security scanning via static analysis, SARIF export, custom analyzers, and LLM-based validation.
Vercel Launches Eve: An Open-Source AI Agent Framework That⭐6
Vercel launches Eve, an open-source AI agent framework that treats each agent as a directory of capability-mapped files—simplifying development, testing, and sc...
MiniMax Sparse Attention (MSA): A Two-Branch Block-Sparse⭐8
MiniMax Sparse Attention (MSA) uses a two-branch block-sparse mechanism to cut compute 80-90%, trained on a 109B MoE with 3T tokens for efficient long-context L...
OpenAI’s Deployment Simulation Extends Pre-Deployment Risk⭐8
OpenAI has introduced a new pre-deployment safety method called Deployment Simulation. The approach is straightforward: before shipping a model, simulat...
How to Build Memory-Efficient Transformers with xFormers: A⭐8
Build memory-efficient Transformers with xFormers: packed sequences, GQA, ALiBi, SwiGLU & causal attention. Reduce GPU memory 30-50% and speed up long-context m...
Meet Qwen-RobotSuite: Three Embodied AI Models for VLA⭐7
Qwen-RobotSuite: Three AI models for VLA manipulation, video world modeling, and navigation, built on a Qwen vision-language backbone for embodied robotics.