Working paper library

Protocol-Guided Autonomous Research with Claude Code

Scientific Verification, Reproducibility, and the Cost of Delegation: A Controlled Study

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

Instruction files that steer coding agents through research tasks range from one sentence to several thousand words of phases, gates and integrity rules, but whether that structure changes what the agent delivers has not been measured with the agent held fixed. The paper reports 288 live Claude Code runs (362…

When AI Agents Become Economic Agents: An Agentic General Equilibrium Theory

Simon-Pierre Boucher · UQO Working Papers · October 2026 · v1.0

Households and firms are beginning to delegate economic decisions to autonomous agents built on a few shared foundation models. This paper studies what this does in general equilibrium. A human's decision error is idiosyncratic and averages out; an AI agent's error is common to every principal that uses the same…