# TermiGen: High-Fidelity Environment and Robust Trajectory Synthesis for Terminal Agents

arXiv: https://arxiv.org/abs/2602.07274 · HTML: https://mlsanity.com/paper/2602.07274/

## Key facts

- Cited by 29 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 23 of its 34 references that are in the map.
- First posted on arXiv 6 Feb 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, 23 of 23)

- [Training Verifiers to Solve Math Word Problems](https://mlsanity.com/paper/2110.14168/) (2021)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments](https://mlsanity.com/paper/2404.07972/) (2024)
- [Kimi K2: Open Agentic Intelligence](https://mlsanity.com/paper/2507.20534/) (2025)
- [AgentTuning: Enabling Generalized Agent Abilities for LLMs](https://mlsanity.com/paper/2310.12823/) (2023)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [FireAct: Toward Language Agent Fine-tuning](https://mlsanity.com/paper/2310.05915/) (2023)
- [OpenCodeInterpreter: Integrating Code Generation with Execution and Refinement](https://mlsanity.com/paper/2402.14658/) (2024)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents](https://mlsanity.com/paper/2406.12952/) (2024)
- [AgentInstruct: Toward Generative Teaching with Agentic Flows](https://mlsanity.com/paper/2407.03502/) (2024)
- [Simulating Environments with Reasoning Models for Agent Training](https://mlsanity.com/paper/2511.01824/) (2025)
- [Scaling Agent Learning via Experience Synthesis](https://mlsanity.com/paper/2511.03773/) (2025)
- [Competition-Level Problems are Effective LLM Evaluators](https://mlsanity.com/paper/2312.02143/) (2023)
- [LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training](https://mlsanity.com/paper/2510.14969/) (2025)
- [DevOps-Gym: Benchmarking AI Agents in Software DevOps Cycle](https://mlsanity.com/paper/2601.20882/) (2026)

## Built on by (most cited first, 29 of 29)

- [Tmax: A simple recipe for terminal agents](https://mlsanity.com/paper/2606.23321/) (2026)
- [Qwen-AgentWorld: Language World Models for General Agents](https://mlsanity.com/paper/2606.24597/) (2026)
- [Terminal-World: Scaling Terminal-Agent Environments via Agent Skills](https://mlsanity.com/paper/2605.20876/) (2026)
- [Recursive Synthesis for Long-Horizon Terminal Tasks](https://mlsanity.com/paper/2608.05466/) (2026)
- [Failure as a Process: An Anatomy of CLI Coding Agent Trajectories](https://mlsanity.com/paper/2607.09510/) (2026)
- [CLI-Universe: Towards Verifiable Task Synthesis Engine for Terminal Agents](https://mlsanity.com/paper/2606.22883/) (2026)
- [SETA: Scaling Environments for Terminal Agents](https://mlsanity.com/paper/2607.10891/) (2026)
- [SPADE: Self-Play in Adaptive Synthetic Executable Environments](https://mlsanity.com/paper/2608.19197/) (2026)
- [OpenComputer: Verifiable Software Worlds for Computer-Use Agents](https://mlsanity.com/paper/2605.19769/) (2026)
- [TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks](https://mlsanity.com/paper/2605.22535/) (2026)
- [What Makes Interaction Trajectories Effective for Training Terminal Agents?](https://mlsanity.com/paper/2606.03461/) (2026)
- [KAT-Coder-V2 Technical Report](https://mlsanity.com/paper/2603.27703/) (2026)
- [LiteCoder-Terminal: Scaling Long-Horizon Terminal Environments for Learning Language Agents](https://mlsanity.com/paper/2605.29559/) (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)
- [T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks](https://mlsanity.com/paper/2609.11042/) (2026)
- [Meta-Task: Turning Terminal Task Synthesis into a Terminal Task for Scalable Agent Training](https://mlsanity.com/paper/2607.27929/) (2026)
- [Envs-FORGE: Frontier-Optimized Reward-Grounded Environment Synthesis for Agent RL](https://mlsanity.com/paper/2608.14312/) (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)
- [Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World](https://mlsanity.com/paper/2605.26086/) (2026)
- [ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories](https://mlsanity.com/paper/2606.11520/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [SelfOp: An Optimization Algorithm for Self-Improving Security Agents](https://mlsanity.com/paper/2609.22792/) (2026)
- [Can Terminal Agents Trust Their Own Verification? Diagnosing and Improving Self-Verification](https://mlsanity.com/paper/2609.38812/) (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)
- [SkillForgeBench: Evaluating Agent Reliability Grounded in Agent Skill Specifications](https://mlsanity.com/paper/2610.14918/) (2026)
- [ReTerm: Recovery Training for Self-Improving Terminal Agents](https://mlsanity.com/paper/2610.18484/) (2026)

## Abstract (arXiv)

Executing complex terminal tasks remains a significant challenge for open-weight LLMs, constrained by two fundamental limitations. First, high-fidelity, executable training environments are scarce: environments synthesized from real-world repositories are not diverse and scalable, while trajectories synthesized by LLMs suffer from hallucinations. Second, standard instruction tuning uses expert trajectories that rarely exhibit simple mistakes common to smaller models. This creates a distributional mismatch, leaving student models ill-equipped to recover from their own runtime failures. To bridge these gaps, we introduce TermiGen, an end-to-end pipeline for synthesizing verifiable environments and resilient expert trajectories. Termi-Gen first generates functionally valid tasks and Docker containers via an iterative multi-agent refinement loop. Subsequently, we employ a Generator-Critic protocol that actively injects errors during trajectory collection, synthesizing data rich in error-correction cycles. Fine-tuned on this TermiGen-generated dataset, our TermiGen-Qwen2.5-Coder-32B achieves a 31.3% pass rate on TerminalBench. This establishes a new open-weights state-of-the-art, outperforming existing baselines and notably surpassing capable proprietary models such as o4-mini. Dataset is avaiable at https://github.com/ucsb-mlsec/terminal-bench-env.