Agent Eng News

Sunday, September 27, 2026 · Past edition · 8 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
Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents
Counterfactual Rollout Replay gives selected software-agent decisions a step-level return contrast by replaying alternative actions in forkable environments.
Why it matters: CRR can add intermediate decision signal without human process labels or a learned process reward model. Its practical value depends on affordable, reliable state restoration, and replay compute is not free.
Original · arxiv (new tab)Read
Research & academia
Research & academia
Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models

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

Counterfactual Rollout Replay: Forkable Environments as Free Process Rewards for Software Engineering Agents

Research & academia

Identical Runs, Different Results: Benchmarking AI Coding Agents on Open-Weight Models

Keep notes on the stories you read

WideSWE: Can Coding Agents Coordinate Changes Across Repositories?

Marathoner: Ultra-Long-Horizon Autonomous Intelligence