# SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation

arXiv: https://arxiv.org/abs/2510.07733 · HTML: https://mlsanity.com/paper/2510.07733/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 12 of its 24 references that are in the map.
- First posted on arXiv 9 Oct 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 12 of 12)

- [LongBench: A Bilingual, Multitask Benchmark for Long Context Understanding](https://mlsanity.com/paper/2308.14508/) (2023)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models](https://mlsanity.com/paper/2305.04091/) (2023)
- [From Louvain to Leiden: guaranteeing well-connected communities](https://mlsanity.com/paper/1810.08473/) (2018)
- [Inference Scaling Laws: An Empirical Analysis of Compute-Optimal Inference for Problem-Solving with Language Models](https://mlsanity.com/paper/2408.00724/) (2024)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [LongAlign: A Recipe for Long Context Alignment of Large Language Models](https://mlsanity.com/paper/2401.18058/) (2024)
- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)
- [Automating Research Synthesis with Domain-Specific Large Language Model Fine-Tuning](https://mlsanity.com/paper/2404.08680/) (2024)
- [Artificial Intelligence for the Metaverse: A Survey](https://mlsanity.com/paper/2202.10336/) (2022)
- [InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System](https://mlsanity.com/paper/2504.08762/) (2025)
- [Scientific Paper Retrieval with LLM-Guided Semantic-Based Ranking](https://mlsanity.com/paper/2505.21815/) (2025)

## Built on by (most cited first, 10 of 10)

- [AI for Auto-Research: Roadmap & User Guide](https://mlsanity.com/paper/2605.18661/) (2026)
- [ScholarPeer: A Context-Aware Multi-Agent Framework for Automated Peer Review](https://mlsanity.com/paper/2601.22638/) (2026)
- [SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation](https://mlsanity.com/paper/2602.11238/) (2026)
- [DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability](https://mlsanity.com/paper/2605.29522/) (2026)
- [Making AI Scientists Auditable from Evidence to Claim](https://mlsanity.com/paper/2606.18874/) (2026)
- [Telling Speculative Stories to Help Humans Imagine the Harms of Healthcare AI](https://mlsanity.com/paper/2510.14718/) (2025)
- [MVSS: A Unified Framework for Multi-View Structured Survey Generation](https://mlsanity.com/paper/2601.09504/) (2026)
- [Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrieval](https://mlsanity.com/paper/2601.15170/) (2026)
- [SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentation](https://mlsanity.com/paper/2609.05938/) (2026)
- [What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agents](https://mlsanity.com/paper/2609.32318/) (2026)

## Abstract (arXiv)

Large language models (LLMs) are increasingly adopted for automating survey paper generation citewang2406autosurvey, liang2025surveyx, yan2025surveyforge,su2025benchmarking,wen2025interactivesurvey. Existing approaches typically extract content from a large collection of related papers and prompt LLMs to summarize them directly. However, such methods often overlook the structural relationships among papers, resulting in generated surveys that lack a coherent taxonomy and a deeper contextual understanding of research progress. To address these shortcomings, we propose SurveyG, an LLM-based agent framework that integrates textithierarchical citation graph, where nodes denote research papers and edges capture both citation dependencies and semantic relatedness between their contents, thereby embedding structural and contextual knowledge into the survey generation process. The graph is organized into three layers: Foundation, Development, and Frontier, to capture the evolution of research from seminal works to incremental advances and emerging directions. By combining horizontal search within layers and vertical depth traversal across layers, the agent produces multi-level summaries, which are consolidated into a structured survey outline. A multi-agent validation stage then ensures consistency, coverage, and factual accuracy in generating the final survey. Experiments, including evaluations by human experts and LLM-as-a-judge, demonstrate that SurveyG outperforms state-of-the-art frameworks, producing surveys that are more comprehensive and better structured to the underlying knowledge taxonomy of a field.