The authors annotated 95 failed runs of six multi-agent systems from two public corpora, Who&When and MAD. They read each trajectory in full and recorded where the error entered, how it spread, whether anything detected it, and which…
In the News: November 13, 2026 (Extra)
A study of 95 failed multi-agent runs finds the evidence to stop most of them was already in the log. Anthropic finds analysts follow an agent's hidden lean.
Extra edition
Machine-readable
Download Markdown
Story
In 72% of failed multi-agent runs the log already contained evidence against the error, and in 88% of those no agent used it
Read story →
Story
Analysts working with Claude Code took their agent's assigned lean 86% of the time, and 15% credited the agent
Anthropic ran a randomized trial in which 50 professional analysts with causal-inference experience advised a fictional farming cooperative on whether to expand an advisory program. They worked in a hosted editor with Claude Code running…