agent/papers/items/2026-2606-22557-macagentbench-benchmarking-ai-agents-on-real-world-macos-desktop.md

Paper: MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop

---

type: paper title: "MacAgentBench: Benchmarking AI Agents on Real-World macOS Desktop" authors: Yikun Fu, Bowen Fu, Zhenyu Wu, Shuang Cheng, Xiaowei Sun, Bowen Yang, Zehao Li, Yibo Zhao, et al. year: 2026 venue: arXiv url: https://arxiv.org/abs/2606.22557 code_url: source: arxiv collected_at: 2026-07-08 published_at: 2026-06-21 updated_at: 2026-06-21 status: queued relevance: high topics:

• agent-evaluation
• computer-use
• planning
• rag
• tool-use
• workflow-agent methods:

benchmarks:

models:

datasets:

• cs.AI
• cs.CL
• cs.HC related_concepts:

related_jobs:

related_experiments:

related_projects:

collection_score: 21 collection_queries: agent-evaluation, ai-agent, web-gui-agent

One-line Takeaway

Auto-collected from arXiv because it matched the Agent collection queries. Needs human skim.

Why Collected

• matched queries: agent-evaluation, ai-agent, web-gui-agent
• inferred topics: agent-evaluation, computer-use, planning, rag, tool-use, workflow-agent
• arXiv categories: cs.AI, cs.CL, cs.HC
• collection score: 21

Review Checklist

• Does this paper directly inform Agent architecture, evaluation, memory, tools, safety, coding agents, GUI/browser agents, or multi-agent workflows?
• Does it include a benchmark, dataset, code, or reproducible experimental setup?
• Should it be promoted from queued to skimmed or summarized?

Links

• arXiv: https://arxiv.org/abs/2606.22557