elvis@omarsar0 · XAI 摘要
微软新论文引入DELEGATE-52基准，模拟52个专业领域的长文档编辑工作流。测试19个模型，包括Gemini 3.1 Pro、Claude 4.6 Opus和GPT-5.4等前沿模型，发现在长工作流结束时平均损坏25%的文档内容。代理工具使用未能改善表现。论文还提供了其他相关见解。
NEW paper from Microsoft.
This is an important read. （bookmark it）
The work introduces DELEGATE-52， a benchmark simulating long document-editing workflows across 52 professional domains like coding， crystallography， and music notation.
Across 19 tested models， even frontier ones （Gemini 3.1 Pro， Claude 4.6 Opus， GPT-5.4） corrupted an average of 25% of document content by the end of long workflows. Agentic tool use didn't help.
Lots of other insights in this one.
Check it out below…
Paper： https://arxiv.org/abs/2604.15597
Learn to build effective AI agents in our academy： https://academy.dair.ai/