🧠机器之心•Stalecollected in 18h
CLI-Gym Boosts Terminal-Bench by 20%
#agent-bench#data-scaling#docker-envscli-gymcli-gymterminal-benchlibercoderhuawei
💡20% Terminal-Bench jump via open data pipeline—scale your CLI agents now
⚡ 30-Second TL;DR
What Changed
1655 high-reliability CLI task Docker environments from 29 base images
Why It Matters
Breaks data bottleneck for env-interactive agents, narrowing open vs closed model gap. Enables scalable Agentic Coding beyond code-gen.
What To Do Next
Clone CLI-Gym GitHub repo and fine-tune on your Terminal-Bench agents.
Who should care:Researchers & Academics
Key Points
- •1655 high-reliability CLI task Docker environments from 29 base images
- •291 success trajectories yield 20%+ solve rate boost on Terminal-Bench
- •LiberCoder-32B: +28.6% to 38.9%; 235B: +21.1% to 46.1%
- •Automates env degradation for problem+test generation
📰
Weekly AI Recap
Read this week's curated digest of top AI events →
👉Related Updates
AI-curated news aggregator. All content rights belong to original publishers.
Original source: 机器之心 ↗
This is a summary, not the original. Read the source, or get the weekly briefing.
Weekly AI briefing
One email a week. Unsubscribe anytime.