INSIGHT AI

Source-linked text edition ·

SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories

The written, source-linked counterpart to this video.

Spoken scripts · Report and scripts (PDF)

Published edition1 story

SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories

AI Agents are becoming digital coworkers that can browse the web, write code, run experiments, and assist humans over extended horizons.

The arXiv coding-agent research feed release records 2611.05512v1 for arXiv.

Source evidence for SlackBench: Benchmarking Agents on Collaborative Projects Grounded in Real Code Repositories
Source-linked proof · original source

Video edition · Markdown edition

Source ledger