# Role-Augmented Intent-Driven Generative Search Engine Optimization

arXiv: https://arxiv.org/abs/2508.11158 · HTML: https://mlsanity.com/paper/2508.11158/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in RAG pipeline design and evaluation, one of 15 directions in Retrieval-augmented generation.
- Builds on 15 of its 32 references that are in the map.
- First posted on arXiv 15 Aug 2025.

## Placed in

- Retrieval-augmented generation / [RAG pipeline design and evaluation](https://mlsanity.com/rag/rag-pipeline-design-and-evaluation/)

## Builds on (most cited first, 15 of 15)

- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [G-Eval: NLG Evaluation using GPT-4 with Better Human Alignment](https://mlsanity.com/paper/2303.16634/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [Learning Intents behind Interactions with Knowledge Graph for Recommendation](https://mlsanity.com/paper/2102.07057/) (2021)
- [Large Language Models Know Your Contextual Search Intent: A Prompting Framework for Conversational Search](https://mlsanity.com/paper/2303.06573/) (2023)
- [Self-Contrast: Better Reflection Through Inconsistent Solving Perspectives](https://mlsanity.com/paper/2401.02009/) (2024)
- [RewriteLM: An Instruction-Tuned Large Language Model for Text Rewriting](https://mlsanity.com/paper/2305.15685/) (2023)
- [Learning to Rewrite Prompts for Personalized Text Generation](https://mlsanity.com/paper/2310.00152/) (2023)
- [Large Language Models for Intent-Driven Session Recommendations](https://mlsanity.com/paper/2312.07552/) (2023)
- [Manipulating Large Language Models to Increase Product Visibility](https://mlsanity.com/paper/2404.07981/) (2024)
- [Ranking Manipulation for Conversational Search Engines](https://mlsanity.com/paper/2406.03589/) (2024)
- [Auto-Intent: Automated Intent Discovery and Self-Exploration for Large Language Model Web Agents](https://mlsanity.com/paper/2410.22552/) (2024)
- [Conversational User-AI Intervention: A Study on Prompt Rewriting for Improved LLM Response Generation](https://mlsanity.com/paper/2503.16789/) (2025)
- [DeepThink: Aligning Language Models with Domain-Specific User Intents](https://mlsanity.com/paper/2502.05497/) (2025)

## Built on by (most cited first, 5 of 5)

- [Caption Injection for Optimization in Generative Search Engine](https://mlsanity.com/paper/2511.04080/) (2025)
- [GEO-Flag: Detecting and Measuring GEO-Optimized Web Content](https://mlsanity.com/paper/2608.16824/) (2026)
- [The End of Rented Discovery: How AI Search Redistributes Power Between Hotels and Intermediaries](https://mlsanity.com/paper/2603.20062/) (2026)
- [Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes](https://mlsanity.com/paper/2608.11390/) (2026)
- [Query Implied Generative Engine Optimization](https://mlsanity.com/paper/2609.27845/) (2026)

## Abstract (arXiv)

Generative Search Engines (GSEs), powered by Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG), are reshaping information retrieval. While commercial systems (e.g., BingChat, Perplexity.ai) demonstrate impressive semantic synthesis capabilities, their black-box nature fundamentally undermines established Search Engine Optimization (SEO) practices. Content creators face a critical challenge: their optimization strategies, effective in traditional search engines, are misaligned with generative retrieval contexts, resulting in diminished visibility. To bridge this gap, we propose a Role-Augmented Intent-Driven Generative Search Engine Optimization (G-SEO) method, providing a structured optimization pathway tailored for GSE scenarios. Our method models search intent through reflective refinement across diverse informational roles, enabling targeted content enhancement. To better evaluate the method under realistic settings, we address the benchmarking limitations of prior work by: (1) extending the GEO dataset with diversified query variations reflecting real-world search scenarios and (2) introducing G-Eval 2.0, a 6-level LLM-augmented evaluation rubric for fine-grained human-aligned assessment. Experimental results demonstrate that search intent serves as an effective signal for guiding content optimization, yielding significant improvements over single-aspect baseline approaches in both subjective impressions and objective content visibility within GSE responses.