Agent Eng News

Tuesday, September 8, 2026 · Past edition · 12 stories

Retrospective edition reconstructed from later captures. Paper versions may include later updates; coverage labels describe the evidence used.

Browse published editions

Filter by topic · Research & academia

Lead stories
Research & academia
ExecCritic: Learn to Test, Test to Improve for Coding Agents
ExecCritic separates test creation from code repair because execution feedback helps only when tests correctly capture the issue’s requested behavior.
Why it matters: For coding-agent systems, adding tests is not automatically beneficial: test quality can determine whether execution feedback improves repairs or misleads the agent. ExecCritic’s reported results make independent test construction and qualification central design choices.
Original · arxiv (new tab)Read
Research & academia
Research & academia
Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

Keep notes on the stories you read

Open each story in the reader. Summaries are shown when available; some sources provide an abstract only. With an account you can keep your own notes.

Personal notes on the sources you read, tied to your account
A Library to come back to, with export to Markdown, Notion or Obsidian
AI questions and rewrites on accounts with AI tools enabled

How Reading + AI works

Agent Eng News

Lead stories

ExecCritic: Learn to Test, Test to Improve for Coding Agents

Research & academia

Co-Evolving Harnesses and Models: On-Policy Correction Helps Weaker Models Catch Up Where Imitation Fails

Keep notes on the stories you read