mlsanityData to 7 Oct 2026

SafeGEO: Understanding Generative Engine Optimization Risks in Recommendation Agents

arXiv 2606.28356 ↗First posted 8 Jun 2026cs.IR cs.AIcited by 4

Not on the map. Why?

Abstract (arXiv)

Generative Engine Optimization (GEO) lets content owners rewrite web content to increase their visibility in generative systems. In recommendation agents, this creates a risk that sources controlled by sellers make flawed products appear better supported than they are. We study this risk at the generation stage by asking whether recommendation agents continue to make decisions that align with user utility when these sources are rewritten for GEO. To make this question measurable, we construct SafeGEO, an evaluation suite with 22 GEO attack variants across 600 recommendation cases. We empirically show that GEO attacks can promote flawed target products: they increase the rate at which such flawed products enter the recommendation set by up to 83.2 percentage points (pp). We further study whether agent-side design choices can mitigate this risk and show that simple defenses reduce harmful target promotion by up to 39.2 pp. These gains are substantial but do not restore the no-GEO performance, showing that GEO remains a serious risk despite mitigation.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 31 of its 63 references that are in the map. First posted on arXiv 8 Jun 2026.

Builds on

31 of 63 references.

References · 31

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  6. 2023Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injectioncited by 1,339
  7. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  8. 2026DeepSeek-V4: Towards Highly Efficient Million-Token Context Intelligencecited by 877
  9. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  10. 2022Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)cited by 396
  11. 2023A Survey on Large Language Models for Recommendationcited by 378
  12. 2023TALLRec: An Effective and Efficient Tuning Framework to Align Large Language Model with Recommendationcited by 336
19 more
  1. 2021Measuring Attribution in Natural Language Generation Modelscited by 253
  2. 2024Actions Speak Louder than Words: Trillion-Parameter Sequential Transducers for Generative Recommendationscited by 184
  3. 2025OneRec: Unifying Retrieve and Rank with Generative Recommender and Iterative Preference Alignmentcited by 167
  4. 2023RecRanker: Instruction Tuning Large Language Model as Ranker for Top-k Recommendationcited by 36
  5. 2024Elaborative Subtopic Query Reformulation for Broad and Indirect Queries in Travel Destination Recommendationcited by 11
  6. 2025MA-DPR: Manifold-aware Distance Metrics for Dense Passage Retrievalcited by 8
  7. 2025A Simple but Effective Elaborative Query Reformulation Approach for Natural Language Recommendationcited by 8
  8. 2025Multimodal Item Scoring for Natural Language Recommendation via Gaussian Process Regression with LLM Relevance Judgmentscited by 8
  9. 2025ChessQA: Evaluating Large Language Models for Chess Understandingcited by 8
  10. 2025E-GEO: A Testbed for Generative Engine Optimization in E-Commercecited by 8
  11. 2026Semantic XPath: Structured Agentic Memory Access for Conversational AIcited by 6
  12. 2026SAGEO Arena: A Realistic Environment for Evaluating Search-Augmented Generative Engine Optimizationcited by 5
  13. 2026Grounded Chess Reasoning in Language Models via Master Distillationcited by 5
  14. 2026ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinementcited by 5
  15. 2026Bayesian Active Learning with Gaussian Processes Guided by LLM Relevance Scoring for Dense Passage Retrievalcited by 5
  16. 2021POINTREC: A Test Collection for Narrative-driven Point of Interest Recommendationcited by 4
  17. 2026Evaluating Scene-based In-Situ Item Labeling for Immersive Conversational Recommendationcited by 4
  18. 2026Is Your LLM-as-a-Recommender Agent Trustable? LLMs' Recommendation is Easily Hacked by Biases (Preferences)cited by 3
  19. 2026Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systemscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 4.

4 papers.

  1. 2026GEO-Flag: Detecting and Measuring GEO-Optimized Web Contentcited by 2
  2. 2026MicroVerse: An Instrument for Measuring Self-Authored Identity Drift in Long-Horizon Multi-Agent Language-Model Simulationscited by 1
  3. 2026Evaluating Deep-Search Agents under Hierarchical Web Evidence Poisoningcited by 1
  4. 2026Agent Safety From Within: Detecting Harmful Trajectories from LLM Internal Statescited by 0