Siheng Chen

MIRA proposes a novel source-aware filtering framework that discovers and anchors evaluation rubrics during data selection, significantly improving code-oriented mid-training data quality while reducing token usage.

The paper introduces MCP-Persona, a novel benchmark designed to evaluate LLM agents' performance on real-world, personalized applications using the Model Context Protocol (MCP), revealing that current state-of-the-art agents struggle with such personalized tool use.