# What Generative Search Engines Like and How to Optimize Web Content Cooperatively

arXiv: https://arxiv.org/abs/2510.11438 · HTML: https://mlsanity.com/paper/2510.11438/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 13 Oct 2025.

## Built on by (most cited first, 13 of 13)

- [Agent Skills: A Data-Driven Analysis of Claude Skills for Extending Large Language Model Functionality](https://mlsanity.com/paper/2602.08004/) (2026)
- [AgentWebBench: Benchmarking Multi-Agent Coordination in Agentic Web](https://mlsanity.com/paper/2604.10938/) (2026)
- [Diagnosing and Repairing Citation Failures in Generative Engine Optimization](https://mlsanity.com/paper/2603.09296/) (2026)
- [Think Before Writing: Feature-Level Multi-Objective Optimization for Generative Citation Visibility](https://mlsanity.com/paper/2604.19113/) (2026)
- [EcoGEO: Trajectory-Aware Evidence Ecosystems for Web-Enabled LLM Search Agents](https://mlsanity.com/paper/2605.12887/) (2026)
- [PILA: Plug-and-Play Insertion for LLM-native Advertising](https://mlsanity.com/paper/2607.25590/) (2026)
- [GEO-Flag: Detecting and Measuring GEO-Optimized Web Content](https://mlsanity.com/paper/2608.16824/) (2026)
- [When Optimization Becomes Manipulation: Defending Generative Search against Malicious Generative Engine Optimization](https://mlsanity.com/paper/2609.02964/) (2026)
- [Exploring LLM biases to manipulate AI search overview](https://mlsanity.com/paper/2605.00012/) (2026)
- [One Polluted Page Is Enough: Evaluating Web Content Pollution in LLM Recommenders](https://mlsanity.com/paper/2606.13610/) (2026)
- [Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes](https://mlsanity.com/paper/2608.11390/) (2026)
- [CHASE: How Content Ecosystems Are Reshaped When Ranking Is the Only Target](https://mlsanity.com/paper/2608.30466/) (2026)
- [A Shared Taste for Model-Written Text: The Generator-by-Selector Matrices of "AI-AI Bias" Show No Detectable Own-Model Premium](https://mlsanity.com/paper/2610.00369/) (2026)

## Abstract (arXiv)

By employing large language models (LLMs) to retrieve documents and generate natural language responses, Generative Engines, such as Google AI overview and ChatGPT, provide significantly enhanced user experiences and have rapidly become the new form of search. Their rapid adoption also drives the needs of Generative Engine Optimization (GEO), as content providers are eager to gain more traction from them. In this paper, we introduce AutoGEO, a framework to automatically learn generative engine preferences when using retrieved contents for response generation, and rewrite web contents for more such traction. AutoGEO first prompts frontier LLMs to explain generative engine preferences and extract meaningful preference rules from these explanations. Then it uses preference rules as context engineering for AutoGEOAPI, a prompt-based GEO system, and as rule-based rewards to train AutoGEOMini, a cost-effective GEO model. Experiments on the standard GEO-Bench and two newly constructed benchmarks using real user queries demonstrate the effectiveness of AutoGEO in enhancing content traction while preserving search utility. Analyses confirm the learned rules' robustness and abilities to capture unique preferences in variant domains, and AutoGEO systems' ability to embed them in content optimization. The code is released at https://github.com/cxcscmu/AutoGEO.