# Tmax: A simple recipe for terminal agents

arXiv: https://arxiv.org/abs/2606.23321 · HTML: https://mlsanity.com/paper/2606.23321/

## Key facts

- Cited by 27 papers in the map (data through 13 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 32 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, 18 of 18)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [Scaling Synthetic Data Creation with 1,000,000,000 Personas](https://mlsanity.com/paper/2406.20094/) (2024)
- [Training Software Engineering Agents and Verifiers with SWE-Gym](https://mlsanity.com/paper/2412.21139/) (2024)
- [SWE-smith: Scaling Data for Software Engineering Agents](https://mlsanity.com/paper/2504.21798/) (2025)
- [MiniMax-M1: Scaling Test-Time Compute Efficiently with Lightning Attention](https://mlsanity.com/paper/2506.13585/) (2025)
- [SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents](https://mlsanity.com/paper/2505.20411/) (2025)
- [NL2Bash: A Corpus and Semantic Parser for Natural Language Interface to the Linux Operating System](https://mlsanity.com/paper/1802.08979/) (2018)
- [Endless Terminals: Scaling RL Environments for Terminal Agents](https://mlsanity.com/paper/2601.16443/) (2026)
- [On Data Engineering for Scaling LLM Terminal Capabilities](https://mlsanity.com/paper/2602.21193/) (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)
- [SWE-Universe: Scale Real-World Verifiable Environments to Millions](https://mlsanity.com/paper/2602.02361/) (2026)
- [Computer Environments Elicit General Agentic Intelligence in LLMs](https://mlsanity.com/paper/2601.16206/) (2026)
- [SERA: Soft-Verified Efficient Repository Agents](https://mlsanity.com/paper/2601.20789/) (2026)

## Built on by (most cited first, 27 of 27)

- [Nanbeige4.2-3B: Unlocking Agentic Capabilities in a Compact Model](https://mlsanity.com/paper/2607.22083/) (2026)
- [Recursive Synthesis for Long-Horizon Terminal Tasks](https://mlsanity.com/paper/2608.05466/) (2026)
- [CalibForge: Adversarial Solver Calibration for Scaling Learnable Terminal Tasks](https://mlsanity.com/paper/2608.06352/) (2026)
- [FACET: Preserving Source Intent and Executable State in Terminal Task Synthesis](https://mlsanity.com/paper/2608.18580/) (2026)
- [Terminal-Universe: Turning Agent Trajectories into Scalable Terminal Environments](https://mlsanity.com/paper/2609.04148/) (2026)
- [FrogNano: Training a 4B Coding Agent via Online Task Synthesis](https://mlsanity.com/paper/2609.07925/) (2026)
- [Learning Generalizable Behaviors for Terminal Agents](https://mlsanity.com/paper/2608.22631/) (2026)
- [T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks](https://mlsanity.com/paper/2609.11042/) (2026)
- [Terminal Agents: A Survey of AI Agents in Command-Line Environments](https://mlsanity.com/paper/2608.20485/) (2026)
- [What Does Multi-Harness RL Learn? Credit Assignment and Portability in Coding Agents](https://mlsanity.com/paper/2609.04518/) (2026)
- [CUA-Universe: A Scalable and Dynamic Environment for Hybrid GUI+CLI Agents](https://mlsanity.com/paper/2609.05374/) (2026)
- [Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents](https://mlsanity.com/paper/2609.39982/) (2026)
- [SearchWiki: Learning to Build and Navigate Knowledge Wikis for Active Information Seeking](https://mlsanity.com/paper/2608.29953/) (2026)
- [Train What You Deploy:Token-Faithful Post-Training of a Production Coding](https://mlsanity.com/paper/2609.04678/) (2026)
- [Training Large Language Models for Small-Molecule Design with Synthetic Task Scaling](https://mlsanity.com/paper/2609.04735/) (2026)
- [Bellman Policy Optimization](https://mlsanity.com/paper/2609.15987/) (2026)
- [Don't Mask the Environment: Observation Supervision Changes How Agents Explore Under RL](https://mlsanity.com/paper/2609.20715/) (2026)
- [Before the Rollout Ends: Early Terminal Reward Prediction for Long-horizon Coding Agents](https://mlsanity.com/paper/2609.31995/) (2026)
- [SoFT: Soft Targets for Generalizable LLM Fine-Tuning](https://mlsanity.com/paper/2609.32493/) (2026)
- [ARISE: Adapting to Evolving Capability Gaps in Agentic Reinforcement Learning](https://mlsanity.com/paper/2609.35532/) (2026)
- [Learning from Teacher Continuations at Student States](https://mlsanity.com/paper/2609.36246/) (2026)
- [When Terminal-Agent Training Stalls: Demystifying Data Generation and Verification Challenge](https://mlsanity.com/paper/2610.02405/) (2026)
- [Self-Supervised Scaling of Terminal Environments for Scientific Domains](https://mlsanity.com/paper/2610.02710/) (2026)
- [Credit Where It Matters: Dependency-Aware Policy Optimization for Terminal Agents](https://mlsanity.com/paper/2610.03634/) (2026)
- [CoTrace: Data Recipes for Training Terminal Agents with Harness-Model Co-Evolution](https://mlsanity.com/paper/2610.10426/) (2026)
- [A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching](https://mlsanity.com/paper/2610.10447/) (2026)
- [Which Skill to Distill? SGUID: Selecting a Compact Skill Bank for Model-Skill Co-Evolution](https://mlsanity.com/paper/2610.12367/) (2026)

## Abstract (arXiv)

Terminal-using agents have quickly become the most popular downstream application of language models (LMs). Despite their prevalence, relatively little academic work has examined RL-based training of these models, likely due to difficult benchmarks, a lack of data, and a lack of simple baseline recipes. We present Tmax, the strongest open RL recipe for terminal agents to date, bringing open data recipes closer to the frontier. While simple, our recipe achieves 27% on Terminal-Bench 2.0 with only 9B parameters, outperforming much larger models from prior work. Concretely, we generate data using a novel taxonomy, combining difficulty control, personas, and verifier diversification, which allows us to cheaply generate large amounts of terminal environments for RL and SFT training. We open-source our terminal dataset, which is over 2.5x larger than previously released terminal-agent datasets. We then train open-weight models using RL with our data, using a simple, outcome-only recipe. We release our data, models, and code as a strong baseline for future open academic work on terminal agents at https://github.com/hamishivi/tmax.