---
id: 20261106-T0-03
title: "SlackBench：用真实代码仓库测AI助手能不能当同事"
title_en: "SlackBench Benchmarks AI Agents on Real Code Repository Projects"
url: https://ai.daily.yangsir.net/daily/20261106-T0-03
issue_date: 2026-11-06
publish_date: 2026-11-05T05:00:00.000Z
category: research
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2611.05512
---

# SlackBench：用真实代码仓库测AI助手能不能当同事

AI智能体正从单次任务走向长期协作，但现有评测多用合成数据或孤立任务，无法反映真实知识工作。SlackBench提出基于真实代码仓库的协作项目基准，要求智能体在多人协作、跨任务场景中完成开发工作。这意味着后续模型评测将更贴近真实工作流，开发者可以据此判断智能体在团队协作中的实际可用性。

## English Version

**SlackBench Benchmarks AI Agents on Real Code Repository Projects**

Existing benchmarks for AI agents rely heavily on synthetic data or isolated tasks, failing to capture real knowledge work. SlackBench introduces a benchmark built on real code repositories and collaborative projects, testing whether agents can function as digital coworkers over extended horizons. The benchmark targets multi-person workflows and cross-task continuity, giving developers a more realistic signal for judging agent performance in production team settings.

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2611.05512)

**详情页**：https://ai.daily.yangsir.net/daily/20261106-T0-03

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*