# GenSERP: Large Language Models for Whole Page Presentation

arXiv: https://arxiv.org/abs/2402.14301 · HTML: https://mlsanity.com/paper/2402.14301/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 18 of its 37 references that are in the map.
- First posted on arXiv 22 Feb 2024.

## Builds on (most cited first, 18 of 18)

- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [WebGPT: Browser-assisted question-answering with human feedback](https://mlsanity.com/paper/2112.09332/) (2021)
- [CRITIC: Large Language Models Can Self-Correct with Tool-Interactive Critiquing](https://mlsanity.com/paper/2305.11738/) (2023)
- [Enhancing Retrieval-Augmented Large Language Models with Iterative Retrieval-Generation Synergy](https://mlsanity.com/paper/2305.15294/) (2023)
- [Large Language Models are Effective Text Rankers with Pairwise Ranking Prompting](https://mlsanity.com/paper/2306.17563/) (2023)
- [GPT-4V in Wonderland: Large Multimodal Models for Zero-Shot Smartphone GUI Navigation](https://mlsanity.com/paper/2311.07562/) (2023)
- [RecMind: Large Language Model Powered Agent For Recommendation](https://mlsanity.com/paper/2308.14296/) (2023)
- [Large Language Models as Zero-Shot Conversational Recommenders](https://mlsanity.com/paper/2308.10053/) (2023)
- [Deep Reinforcement Learning for Page-wise Recommendations](https://mlsanity.com/paper/1805.02343/) (2018)
- [Beyond Yes and No: Improving Zero-Shot LLM Rankers via Scoring Fine-Grained Relevance Labels](https://mlsanity.com/paper/2310.14122/) (2023)
- [EduChat: A Large-Scale Language Model-based Chatbot System for Intelligent Education](https://mlsanity.com/paper/2308.02773/) (2023)
- [Synthetic Prompting: Generating Chain-of-Thought Demonstrations for Large Language Models](https://mlsanity.com/paper/2302.00618/) (2023)
- [A Setwise Approach for Effective and Highly Efficient Zero-shot Ranking with Large Language Models](https://mlsanity.com/paper/2310.09497/) (2023)
- [Idea2Img: Iterative Self-Refinement with GPT-4V(ision) for Automatic Image Design and Generation](https://mlsanity.com/paper/2310.08541/) (2023)
- [An Efficient Bandit Algorithm for Realtime Multivariate Optimization](https://mlsanity.com/paper/1810.09558/) (2018)
- [PaRaDe: Passage Ranking using Demonstrations with Large Language Models](https://mlsanity.com/paper/2310.14408/) (2023)
- [Ranking for Relevance and Display Preferences in Complex Presentation Layouts](https://mlsanity.com/paper/1805.02404/) (2018)
- [Tile Networks: Learning Optimal Geometric Layout for Whole-page Recommendation](https://mlsanity.com/paper/2303.01671/) (2023)

## Built on by (most cited first, 1 of 1)

- [InterDeepResearch: Enabling Human-Agent Collaborative Information Seeking through Interactive Deep Research](https://mlsanity.com/paper/2603.12608/) (2026)

## Abstract (arXiv)

The advent of large language models (LLMs) brings an opportunity to minimize the effort in search engine result page (SERP) organization. In this paper, we propose GenSERP, a framework that leverages LLMs with vision in a few-shot setting to dynamically organize intermediate search results, including generated chat answers, website snippets, multimedia data, knowledge panels into a coherent SERP layout based on a user's query. Our approach has three main stages: (1) An information gathering phase where the LLM continuously orchestrates API tools to retrieve different types of items, and proposes candidate layouts based on the retrieved items, until it's confident enough to generate the final result. (2) An answer generation phase where the LLM populates the layouts with the retrieved content. In this phase, the LLM adaptively optimize the ranking of items and UX configurations of the SERP. Consequently, it assigns a location on the page to each item, along with the UX display details. (3) A scoring phase where an LLM with vision scores all the generated SERPs based on how likely it can satisfy the user. It then send the one with highest score to rendering. GenSERP features two generation paradigms. First, coarse-to-fine, which allow it to approach optimal layout in a more manageable way, (2) beam search, which give it a better chance to hit the optimal solution compared to greedy decoding. Offline experimental results on real-world data demonstrate how LLMs can contextually organize heterogeneous search results on-the-fly and provide a promising user experience.