English(EN) Conversational Capture: A Trajectory-Level Framework for Evaluating Generative Engine Optimization in Multi-turn Human-Agent Interaction

新框架评估多轮人工智能交互中的生成引擎优化

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-30 16:23

一项新的研究论文介绍了一个名为“对话捕获”（Conversational Capture）的框架，用于评估多轮人机交互中生成引擎优化（GEO）的性能。作者认为，当前的单轮评估不足以全面衡量AI的性能，因为AI的响应会影响用户的后续提问，进而影响检索到的信息。该框架将这种闭环系统形式化，引入了轨迹级别的概念来衡量累积可见性、直接收益和反馈收益，以及捕获系数。研究表明，在更长的对话中，反馈效应可能显著超过直接收益，导致超线性收益增长，并且单轮评估与基于轨迹的排名之间存在显著差异。 AI

影响这项研究通过改进衡量和开发多轮对话AI代理的优化方式，可能有助于创建更有效的AI代理。

排序理由该集群包含一篇详细介绍AI系统新颖评估框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.IR (Information Retrieval) 阅读 →

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: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍AI系统新颖评估框架的学术论文。[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, other; 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: 4 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.IR (Information Retrieval) TIER_1 English(EN) · Hiroyuki Sato · 2026-09-30 16:23

对话式捕获：用于评估多轮人机交互中生成引擎优化的轨迹级框架

Generative Engine Optimization (GEO) shapes content to increase its likelihood of being cited by answer engines built on retrieval-augmented large language models. GEO is typically evaluated as a single-turn property: for a fixed query, an evaluator measures a source's visibility…

本文如何被排名

报道来源 [1]

对话式捕获：用于评估多轮人机交互中生成引擎优化的轨迹级框架

相关实体

相关话题