Research & academia
LongRCA Bench: Root-Cause Localization in Long-Horizon Agent Trajectories
LongRCA Bench tests tracing early failures in long agent runs.
Why it matters: A long trace can make the earliest consequential error hard to locate.
Agent Eng News
· Past edition · 6 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
Research & academia
StateM: Reaching 95.3% Raw Accuracy, or a $15 Frontier Run, on Terminal-Bench 2.1 via Harness Scaling
StateM uses durable state, checked transitions and runbooks; the authors report Terminal-Bench results across several models and a separate BusinessBench evaluation.
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