The AI Re-Think Blog

The First Quantitative Framework for Deciding When Multi-Agent Coordination Helps—and When It Hurts Report Series:  AI Productization Deep Dives Report Number:  004 Date:  December 2025 Source Paper:  "Towards a Science of Scaling Agent Systems" (arXiv:2512.08296) Authors:  Yubin Kim et al. (18 authors), Google Research, MIT, Google DeepMind Paper Date:  December 9, 2025 Executive Summary This report analyzes the first rigorous empirical study that transforms architecture sel

The First Large-Scale Study of What Actually Works in Enterprise AI Agent Deployments Report Series:  AI Productization Deep Dives Report Number:  003 Date:  December 2025 Source Paper:  "Measuring Agents in Production" (arXiv:2512.04123) Authors:  Melissa Z. Pan et al. (25 authors), UC Berkeley Paper Date:  December 2, 2025 Executive Summary This report analyzes the first large-scale systematic study of AI agents running in production environments. The Berkeley research team

Design and evaluation of a retrieval-driven MCP selector for large tool registries Paper:  RAG-MCP: Mitigating Prompt Bloat in LLM Tool Selection via Retrieval-Augmented Generation Executive Summary RAG-MCP addresses a critical scalability challenge facing modern LLM systems: the "prompt bloat" problem that emerges when large language models must select from hundreds or thousands of external tools. The paper introduces a Retrieval-Augmented Generation framework that dynamical