Episode
TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents
- Podcast
- Daily Paper Cast
- Published
- Jul 1, 2026
- Duration seconds
- 1363
- Processing state
not_requested- Canonical source
- https://share.transistor.fm/s/2777ff4a
Actions
POST https://stenobird.com/v1/public/podcasts/daily-paper-cast-7079649/episodes/tua-bench-a-benchmark-for-general-purpose-terminal-use-agents/transcription-requests
Idempotently request low-priority transcript generation for this episode.GET https://stenobird.com/podcast/daily-paper-cast-7079649/tua-bench-a-benchmark-for-general-purpose-terminal-use-agents.md
Read the agent-friendly Markdown representation of this episode resource.
Summary
🤗 Upvotes: 44 | cs.SE, cs.AI Authors: Shoufa Chen, Luyuan Wang, Xuan Yang, Zhiheng Liu, Yuren Cong, Yuanfeng Ji, Feiyan Zhou, Xiaohui Zhang, Fanny Yang, Belinda Zeng Title: TUA-Bench: A Benchmark for General-Purpose Terminal-Use Agents Arxiv: http://arxiv.org/abs/2606.28480v1 Abstract: As large language models and harness frameworks continue to advance, agents operating in terminals are increasingly capable of performing a broader range of general computer-use tasks beyond coding. However, existing benchmarks do not adequately evaluate general-purpose terminal computer-use agents (TUAs): general computer-use benchmarks primarily target graphical user interfaces (GUIs), whereas terminal-based benchmarks largely emphasize technical and programming-centric workflows historically native to the shell. We introduce TUA-Bench, a general-purpose benchmark for terminal-use agents. TUA-Bench includes 120 real-world tasks across five task families, covering routine digital activities-including document editing, email management, and live-web information seeking-as well as scientific and engineering workflows co-designed with PhD-level domain experts that require specialized software. This breadth distinguishes TUA-Bench from prior shell-focused or domain-specific benchmarks. Each task is manually designed, runs in a real terminal with a deterministic setup script, and is evaluated by an execution-based scoring protocol. We find that the strongest frontier agent, Claude Code with Claude Opus 4.8 max reasoning effort, achieves 65.8% overall performance, with substantial gaps across both tracks. By providing a broad and realistic evaluation of terminal-use capabilities, TUA-Bench aims to accelerate the transition from narrow, task-specific assistants to general-purpose agents capabl…