Agent Eng News

Wednesday, October 14, 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

Lead stories
Agent frameworks & orchestration
Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents
Doc2Harness shifts evaluation from solving tasks under a fixed harness to engineering the harness itself, then tests the result with deterministic, observable checks.
Why it matters: The benchmark makes harness engineering measurable rather than treating the harness as fixed. Its results show both substantial room for improvement and a recurring failure area: how cross-cutting functionality is divided across modules.
Original · arxiv (new tab)Read
Agent frameworks & orchestration
Agent frameworks & orchestration
Context Engineering with Deep Agents: How To Remember Without Keeping Everything In Context

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

Doc2Harness: Benchmarking LLMs on Long-Horizon Harness Engineering of Coding Agents

Agent frameworks & orchestration

Context Engineering with Deep Agents: How To Remember Without Keeping Everything In Context

Keep notes on the stories you read