An MIT Technology Review report based on a survey of 300 data, AI, and technology executives finds that lack of knowledge is the main reason AI agent projects fail to land, with on average only 34% of agentic AI projects reaching production.
A Hugging Face team has proposed ProvenanceGuard, a source-aware factuality verification layer for MCP agents, which checks after generation whether the sources supporting each claim match the sources the answer states or implies, identifying cross-source confusion.
Google Research's Retrieve-for-Train framework uses offline RL to discover reward-aligned query fan-out and distills it into supervision signals, bypassing LLM token-by-token chain-of-thought inference latency.