# Terminal-World: Scaling Terminal-Agent Environments via Agent Skills

arXiv: https://arxiv.org/abs/2605.20876 · HTML: https://mlsanity.com/paper/2605.20876/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Placed in Agent skill learning and evolution, one of 16 directions in LLM agents and tool use.
- Builds on 38 of its 49 references that are in the map.
- First posted on arXiv 20 May 2026.

## Placed in

- LLM agents and tool use / [Agent skill learning and evolution](https://mlsanity.com/agents/agent-skill-learning-and-evolution/)

## Builds on (most cited first, 30 of 38)

- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [gpt-oss-120b & gpt-oss-20b Model Card](https://mlsanity.com/paper/2508.10925/) (2025)
- [Gorilla: Large Language Model Connected with Massive APIs](https://mlsanity.com/paper/2305.15334/) (2023)
- [SGLang: Efficient Execution of Structured Language Model Programs](https://mlsanity.com/paper/2312.07104/) (2023)
- [DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models](https://mlsanity.com/paper/2512.02556/) (2025)
- [Can LLM Already Serve as A Database Interface? A BIg Bench for Large-Scale Database Grounded Text-to-SQLs](https://mlsanity.com/paper/2305.03111/) (2023)
- [GLM-5: from Vibe Coding to Agentic Engineering](https://mlsanity.com/paper/2602.15763/) (2026)
- [Terminal-Bench: Benchmarking Agents on Hard, Realistic Tasks in Command Line Interfaces](https://mlsanity.com/paper/2601.11868/) (2026)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [SWIFT:A Scalable lightWeight Infrastructure for Fine-Tuning](https://mlsanity.com/paper/2408.05517/) (2024)
- [SkillRL: Evolving Agents via Recursive Skill-Augmented Reinforcement Learning](https://mlsanity.com/paper/2602.08234/) (2026)
- [Tool Learning with Large Language Models: A Survey](https://mlsanity.com/paper/2405.17935/) (2024)
- [ToolACE: Winning the Points of LLM Function Calling](https://mlsanity.com/paper/2409.00920/) (2024)
- [APIGen: Automated Pipeline for Generating Verifiable and Diverse Function-Calling Datasets](https://mlsanity.com/paper/2406.18518/) (2024)
- [APIGen-MT: Agentic Pipeline for Multi-Turn Data Generation via Simulated Agent-Human Interplay](https://mlsanity.com/paper/2504.03601/) (2025)
- [Beyond Ten Turns: Unlocking Long-Horizon Agentic Search with Large-Scale Asynchronous RL](https://mlsanity.com/paper/2508.07976/) (2025)
- [InfiAgent-DABench: Evaluating Agents on Data Analysis Tasks](https://mlsanity.com/paper/2401.05507/) (2024)
- [TableBench: A Comprehensive and Complex Benchmark for Table Question Answering](https://mlsanity.com/paper/2408.09174/) (2024)
- [WebShaper: Agentically Data Synthesizing via Information-Seeking Formalization](https://mlsanity.com/paper/2507.15061/) (2025)
- [SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization](https://mlsanity.com/paper/2604.02268/) (2026)
- [WebExplorer: Explore and Evolve for Training Long-Horizon Web Agents](https://mlsanity.com/paper/2509.06501/) (2025)
- [SimpleDeepSearcher: Deep Information Seeking via Web-Powered Reasoning Trajectory Synthesis](https://mlsanity.com/paper/2505.16834/) (2025)
- [Endless Terminals: Scaling RL Environments for Terminal Agents](https://mlsanity.com/paper/2601.16443/) (2026)
- [Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence](https://mlsanity.com/paper/2604.18292/) (2026)
- [TaskCraft: Automated Generation of Agentic Tasks](https://mlsanity.com/paper/2506.10055/) (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)
- [ToolMind Technical Report: A Large-Scale, Reasoning-Enhanced Tool-Use Dataset](https://mlsanity.com/paper/2511.15718/) (2025)
- [TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents](https://mlsanity.com/paper/2602.07274/) (2026)

## Built on by (most cited first, 20 of 20)

- [WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces](https://mlsanity.com/paper/2606.09426/) (2026)
- [ModularRSI: Modular and Generalizable Recursive Harness Self-Improvement](https://mlsanity.com/paper/2609.14857/) (2026)
- [CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks](https://mlsanity.com/paper/2608.06352/) (2026)
- [Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments](https://mlsanity.com/paper/2609.04148/) (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)
- [Learning Generalizable Behaviors for Terminal Agents](https://mlsanity.com/paper/2608.22631/) (2026)
- [CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents](https://mlsanity.com/paper/2609.05374/) (2026)
- [One Goal, Many Commands: Characterizing Denylist Fragility in AI Agents](https://mlsanity.com/paper/2606.15549/) (2026)
- [FM-Bench: A Benchmark for Long-Horizon Management with Competing Agents](https://mlsanity.com/paper/2608.18423/) (2026)
- [AgentMercury: Your Agent Can Synthesize Verifiable Environments for Business Scenarios at scale](https://mlsanity.com/paper/2608.20634/) (2026)
- [Behavior2Trip: Towards Personalized Travel Planning via User Behavior Trajectory](https://mlsanity.com/paper/2608.26807/) (2026)
- [JarvisGUI: Towards Cross-Device GUI Agents with Dynamic Task Composition](https://mlsanity.com/paper/2609.10451/) (2026)
- [Skill2Env: Capability-Oriented Environment Synthesis from Skills for General Agents](https://mlsanity.com/paper/2609.33772/) (2026)
- [Scaling Verifiable Environments for Long-horizon Work Agents](https://mlsanity.com/paper/2610.04906/) (2026)
- [Selecting Long-Horizon Trajectories for Reliable and Efficient Terminal-Agent Training](https://mlsanity.com/paper/2610.05831/) (2026)
- [Scaling Agentic Data for Long-Horizon Terminal Intelligence](https://mlsanity.com/paper/2610.13166/) (2026)
- [AutoEnvScaling: Automating the Data Flywheel with Terminal Agents](https://mlsanity.com/paper/2610.14163/) (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)

## Abstract (arXiv)

Terminal agents extend Large Language Models with the ability to execute tasks directly in command-line environments, but their progress is bottlenecked by the scarcity of high-quality training data. Existing approaches bootstrap from partial sources such as human-defined seeds or GitHub repositories to instantiate one component and then complete the rest, producing tasks confined to narrow seed distributions, environments misaligned with task semantics, and inefficient trajectories from unguided exploration. To address these limitations, we introduce Terminal-World, a fully automated pipeline that uses agent skills as the central synthesis primitive, which jointly encode what to accomplish, when to apply (preconditions and environment state), and how to execute, enabling task instructions, environments, and teacher trajectories to be co-derived. To further broaden the synthesis space, Terminal-World composes skills into skill teams and skill graphs for multi-role and cross-domain task synthesis. Using this pipeline, we construct 5,723 training environments and train Terminal-World-8B/14B/32B, evaluated across 6 benchmarks where the Terminal-World series consistently outperforms terminal-agent baselines. Notably, using the same teacher model and only 1.2% of the training data, Terminal-World-32B surpasses Nemotron-Terminal-32B on Terminal-Bench 2.0 by +4.5 Pass@1 (31.5) and achieves 43.8 Pass@3.