# Tencent's T1 Targets Long-Horizon Terminal Work

> A 122B mixture-of-experts model trained with reinforcement learning claims state-of-the-art results on Terminal-Bench.

Published by The Open Weights on Sep 9, 2026. Canonical: https://theopenweights.com/news/t1-terminal-agent-qet4

## Key facts

- Company: Tencent
- Model: T1 (Terminal Agent)
- Version: T1
- Category: Reasoning
- Modalities: Reasoning, Code, Text / LLM
- License: Other (Open weights, commercial use allowed)
- Parameters: 122B (mixture of experts)
- Significance: notable
- Published: 2026-09-09
- Last verified: 2026-09-11
- Canonical URL: https://theopenweights.com/news/t1-terminal-agent-qet4

Tencent has introduced T1, a terminal agent built to handle the kind of multi-step command-line work that trips up general-purpose models. The system is a 122-billion-parameter mixture-of-experts model tuned with reinforcement learning specifically for long-horizon tasks, according to the [research paper](https://huggingface.co/papers/2609.11042).

The pitch is squarely about endurance. Most coding and agentic benchmarks reward short bursts of reasoning, but real terminal work — installing dependencies, debugging failed builds, chaining shell commands across many steps — punishes models that lose the thread partway through. T1 is trained to keep its footing over longer sequences, and Tencent reports state-of-the-art results on Terminal-Bench, a benchmark designed to measure exactly that.

## Why it matters

Terminal agents sit at the center of the current push toward autonomous software work, where an assistant is expected to operate a shell rather than just suggest snippets. Reinforcement learning on long-horizon rewards is one of the more promising ways to close the gap between demo-quality performance and reliable execution.

- **Architecture:** 122B-parameter mixture-of-experts design
- **Training:** reinforcement learning aimed at long-horizon terminal tasks
- **Result:** reported SOTA on Terminal-Bench

As with many lab releases, the details that matter most for practitioners — licensing terms, context window, and how the model behaves outside benchmark conditions — will determine how widely T1 gets adopted. For now, it stands as a concrete signal that terminal competence is becoming its own optimization target.

## Get the model

- [HF Papers](https://huggingface.co/papers/2609.11042)

## Sources

- [T1: Terminal Agent Reinforcement Learning for Long-Horizon Tasks](https://huggingface.co/papers/2609.11042) — HF Papers, Sep 9, 2026

---
Source: The Open Weights (https://theopenweights.com/). Aggregated and written by Claude, curated by humans. Cite as: "Tencent's T1 Targets Long-Horizon Terminal Work", The Open Weights, Sep 9, 2026, https://theopenweights.com/news/t1-terminal-agent-qet4