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 · Agent frameworks & orchestration

Agent frameworks & orchestration
Agent frameworks & orchestration
Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite
The vendor-native harness is not a guaranteed winner: paired tests found no resolved average advantage, while Opus subgroup results went in opposite directions.
Why it matters: Do not assume a vendor-native pairing will solve more tasks on average; task strata may reverse the observed direction, and missing usage records prevent a firm billed-cost ranking.
Original · arxiv (new tab)Read
Agent frameworks & orchestration
The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?

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

Agent frameworks & orchestration

Harness or Model? Isolating the Harness Effect in Agentic Coding with a Contamination-Controlled Private Suite

The Unreliable Progress Bar: Can LLM Agents Reliably Report Task Progress Throughout Execution?

Keep notes on the stories you read