Tag
This paper introduces the Agentic Publication Protocol (APP), a format that packages scientific papers with code, data, and agent instructions to improve reproducibility and allow AI agents to interact with and build upon published research.
This paper introduces a self-evolving framework for vision-language models to improve their question-generation capabilities without external supervision, enhancing both question quality and answerer performance.
Santiago (@svpino) highlights AG-UI as the fastest-growing agentic protocol after MCP, a lightweight event-streaming protocol for building user-facing AI agents with support for real-time updates, tool orchestration, shared mutable state, security, UI sync, and now threads for resumable conversations.