研究
逐篇精读 GEO 的奠基论文：领域里的核心概念与术语，源头都在这里。
编辑精选
优化方法
- What Evidence Do Language Models Find Convincing? (Wan et al. 2024)
Alexander Wan, Eric Wallace, Dan Klein · ACL 2024 Main (62nd ACM, Long Papers, pp. 7468–7484) · 2024
ACL 2024 这篇论文给一项反直觉的发现配上了数据：让 LLM 在立场相反的网页来源之间做选择，决定它偏向哪一份的，主要是内容与查询的相关性；人类看重的可信度信号（科学引用、中立语气、正式引用格式），几乎左右不了它的选择。本条附 GEO Wiki 的深度解读与批判。
- GEO: Generative Engine Optimization (Aggarwal et al. 2024)
Pranjal Aggarwal, Vishvak Murahari, Tanmay Rajpurohit, Ashwin Kalyan, Karthik Narasimhan, Ameet Deshpande · KDD 2024 (Proc. 30th ACM SIGKDD) · 2024
KDD 2024 的这篇论文首创了「生成式引擎优化（GEO）」一词，发布了 GEO-bench 基准与可见度指标，并证明内容层面的改写可将内容在 AI 答案中的可见度最高提升 40%。本条附 GEO Wiki 对这一数字适用边界的批判性评估。
延伸阅读
理解机制
- Agentic Retrieval-Augmented Generation: A Survey on Agentic RAG (Singh et al. 2025)
- From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents (Zhang et al. 2025)
- A Survey of LLM-based Deep Search Agents: Paradigm, Optimization, Evaluation, and Challenges (Xi et al. 2025)
优化方法
- Diagnosing and Repairing Citation Failures in Generative Engine Optimization (Tian et al. 2026)
- Think Before Writing: Feature-Level Multi-Objective Optimization for Generative Citation Visibility (Liu & Xu 2026)
- Generative Engine Optimization: A VLM and Agent Framework for Pinterest Acquisition Growth (Zhang et al. 2026)
- EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents (Ye et al. 2026)
- IF-GEO: Conflict-Aware Instruction Fusion for Multi-Query Generative Engine Optimization (2026)
- AgenticGEO: A Self-Evolving Agentic System for Generative Engine Optimization (2026)
- Multimodal Generative Engine Optimization: Rank Manipulation for Vision-Language Model Rankers (Du et al. 2026)
- What Generative Search Engines Like and How to Optimize Web Content Cooperatively (Wu et al. 2025)
- StealthRank: LLM Ranking Manipulation via Stealthy Prompt Optimization (Tang et al. 2025)
- White Hat Search Engine Optimization using Large Language Models (Bardas et al. 2025)
- E-GEO: A Testbed for Generative Engine Optimization in E-Commerce (2025)
- GASLITEing the Retrieval: Exploring Vulnerabilities in Dense Embedding-based Search (Ben-Tov & Sharif 2025)
- Role-Augmented Intent-Driven Generative Search Engine Optimization (Chen et al. 2025)
- Dynamics of Adversarial Attacks on Large Language Model-Based Search Engines (Hu 2025)
- Ranking Manipulation for Conversational Search Engines (Pfrommer et al. 2024)
- Manipulating Large Language Models to Increase Product Visibility (Kumar & Lakkaraju 2024)
度量与评测
- Navigating the Shift: A Comparative Analysis of Web Search and Generative AI Response Generation (Chen et al. 2026)
- Source Coverage and Citation Bias in LLM-based vs. Traditional Search Engines (Zhang et al. 2025)
- PoisonArena: Uncovering Competing Poisoning Attacks in Retrieval-Augmented Generation (Chen et al. 2025)
- Search Engines in an AI Era: The False Promise of Factual and Verifiable Source-Cited Responses (Venkit et al. 2024)
- Evaluation of Retrieval-Augmented Generation: A Survey (Yu et al. 2024)