Meta Launches Pocket App for AI-Generated Interactive Experiences

Alibaba researchers developed SkillWeaver, a framework that reduces token consumption by over 99% when routing AI agents to the correct tools from large libraries. The system uses a three-stage process (decompose, retrieve, compose) combined with Skill-Aware Decomposition to iteratively fetch and evaluate relevant tools rather than exposing agents to entire tool catalogs. This addresses a core challenge in enterprise AI systems where agents must orchestrate multiple tools to complete complex, multi-step workflows.

Mark Zuckerberg told Meta staff at an internal meeting that the company's AI development efforts, particularly around AI agents, are progressing slower than he had anticipated. The statement signals a recalibration of expectations around a technology area Meta has invested heavily in. The disclosure comes as the AI industry broadly grapples with the gap between near-term capabilities and longer-term ambitions.

Z.ai, a Beijing-based AI lab, launched ZCode, a free desktop application designed as an agent-first development environment for its GLM-5.2 model. The tool competes directly with Cursor, Claude Code, GitHub Copilot, and Google's Antigravity in the AI coding market. ZCode's pricing undercuts competitors significantly, with plans starting at $16.20 per month, and includes features like remote control via WeChat and Feishu, reflecting the company's focus on the Chinese developer market.

Researchers at Chen et al. have developed an AI X-ray scientist that autonomously aligns single crystals at a real synchrotron beamline, demonstrating how large language models can enable adaptive closed-loop experimentation at large-scale scientific facilities. The system operates without human intervention, representing a shift toward autonomous scientific discovery at major research infrastructure.