# CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents

arXiv: https://arxiv.org/abs/2606.22883 · HTML: https://mlsanity.com/paper/2606.22883/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 10 of its 13 references that are in the map.
- First posted on arXiv 22 Jun 2026.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 10 of 10)

- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Endless Terminals: Scaling RL Environments for Terminal Agents](https://mlsanity.com/paper/2601.16443/) (2026)
- [VitaBench: Benchmarking LLM Agents with Versatile Interactive Tasks in Real-world Applications](https://mlsanity.com/paper/2509.26490/) (2025)
- [On Data Engineering for Scaling LLM Terminal Capabilities](https://mlsanity.com/paper/2602.21193/) (2026)
- [Large-Scale Terminal Agentic Trajectory Generation from Dockerized Environments](https://mlsanity.com/paper/2602.01244/) (2026)
- [TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents](https://mlsanity.com/paper/2602.07274/) (2026)
- [CLI-Gym: Scalable CLI Task Generation via Agentic Environment Inversion](https://mlsanity.com/paper/2602.10999/) (2026)
- [Toward Scalable Terminal Task Synthesis via Skill Graphs](https://mlsanity.com/paper/2604.25727/) (2026)

## Built on by (most cited first, 12 of 12)

- [Failure as a Process: An Anatomy of CLI Coding Agent Trajectories](https://mlsanity.com/paper/2607.09510/) (2026)
- [CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks](https://mlsanity.com/paper/2608.06352/) (2026)
- [NexForge: Scaling Agent Capabilities through Requirement-Driven Task Synthesis for LLMs](https://mlsanity.com/paper/2607.14186/) (2026)
- [SKT: Skill-Use Training at Scale via Verified Synthetic Data Generation](https://mlsanity.com/paper/2608.02287/) (2026)
- [CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents](https://mlsanity.com/paper/2609.05374/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents](https://mlsanity.com/paper/2609.33772/) (2026)
- [SkillGym: Training Skill-Use Agents with Automatic Verifiable Environment Generation](https://mlsanity.com/paper/2609.37539/) (2026)
- [Scaling Agentic Data for Long-Horizon Terminal Intelligence](https://mlsanity.com/paper/2610.13166/) (2026)
- [WorkBorne: Discovering Agentic Tasks from Real-World Artifact Transitions](https://mlsanity.com/paper/2610.14915/) (2026)
- [SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications](https://mlsanity.com/paper/2610.14918/) (2026)
- [Recursive Environment Scaling for General Long-Horizon Agents](https://mlsanity.com/paper/2610.16397/) (2026)

## Abstract (arXiv)

While recent LLM-based terminal agents have demonstrated promising capabilities, the scarcity of high-quality, executable training data remains a critical bottleneck. Existing synthesis pipelines typically scale by retrofitting surface-level artifacts into tasks, frequently yielding ambiguous instructions, shallow execution paths, and brittle tests that provide weak learning signals. To overcome this, we introduce CLI-Universe, a principled synthesis engine that constructs terminal-agent tasks. CLI-Universe generates candidate tasks by sampling combinations across a multi-dimensional capability taxonomy (domain, skill type, capability, and engineering pillar), then grounds each candidate through evidence-guided deep research over real-world technical materials. To ensure rigorous supervision, validated blueprints are instantiated into Dockerized environments and subjected to a multi-stage executable verification pipeline featuring rubric-gated test construction, hint-conditional filtering, and strict fail-to-pass checking. Across the full pipeline, from candidate generation to verification, approximately two-thirds of candidates are discarded, retaining only those that are genuine, verifiable, and non-trivially challenging. To validate our framework, we instantiate a highly distilled dataset of 6,000 trajectories called CLI-Universe-6K. Remarkably, fine-tuning Qwen3-32B on CLI-Universe-6K achieves 33.4% on Terminal-Bench 2.0. This sets a new state-of-the-art for models trained on open-source data at or below 32B parameters, and outperforms several models an order of magnitude larger, demonstrating the profound data efficiency of structured, high-fidelity synthesis.