English(EN) Can LLMs track state changes over long texts—like an object changing hands or a variable reassignment?

前沿大型语言模型在新的StateBench评估中难以进行状态跟踪

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-03 17:32

一项名为StateBench的新基准测试显示，领先的大型语言模型在跟踪长文本中的状态变化方面存在困难。在最具挑战性的长场景中，GPT-6 Sol和Claude Opus 5.5等前沿模型仅取得了13%或更低的准确率。此次评估凸显了当前大型语言模型在长期上下文和状态跟踪方面的重大局限性。 AI

影响凸显了大型语言模型在保持上下文和跟踪长期交互中的状态方面的关键局限性，可能影响需要长期记忆的应用。

排序理由该项目描述了一个用于评估大型语言模型的新基准，属于研究范畴。[lever_c_demoted from research: ic=1 ai=1.0]

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 13 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该项目描述了一个用于评估大型语言模型的新基准，属于研究范畴。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, model release; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。