# DeepSurvey: Agent-Oriented Automated Survey Generation with Analytical Depth and Citation Reliability

arXiv: https://arxiv.org/abs/2605.29522 · HTML: https://mlsanity.com/paper/2605.29522/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 48 references that are in the map.
- First posted on arXiv 28 May 2026.

## Builds on (most cited first, 22 of 22)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [OpenAI GPT-5 System Card](https://mlsanity.com/paper/2601.03267/) (2025)
- [DeepSeek-V3 Technical Report](https://mlsanity.com/paper/2412.19437/) (2024)
- [SelfCheckGPT: Zero-Resource Black-Box Hallucination Detection for Generative Large Language Models](https://mlsanity.com/paper/2303.08896/) (2023)
- [Prometheus 2: An Open Source Language Model Specialized in Evaluating Other Language Models](https://mlsanity.com/paper/2405.01535/) (2024)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [JudgeLM: Fine-tuned Large Language Models are Scalable Judges](https://mlsanity.com/paper/2310.17631/) (2023)
- [MinerU: An Open-Source Solution for Precise Document Content Extraction](https://mlsanity.com/paper/2409.18839/) (2024)
- [MiniLMv2: Multi-Head Self-Attention Relation Distillation for Compressing Pretrained Transformers](https://mlsanity.com/paper/2012.15828/) (2020)
- [MiMo-V2-Flash Technical Report](https://mlsanity.com/paper/2601.02780/) (2026)
- [Context Length Alone Hurts LLM Performance Despite Perfect Retrieval](https://mlsanity.com/paper/2510.05381/) (2025)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [PINNacle: A Comprehensive Benchmark of Physics-Informed Neural Networks for Solving PDEs](https://mlsanity.com/paper/2306.08827/) (2023)
- [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025)
- [SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation](https://mlsanity.com/paper/2508.15658/) (2025)
- [SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generation](https://mlsanity.com/paper/2506.12689/) (2025)
- [SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation](https://mlsanity.com/paper/2510.07733/) (2025)
- [Lost in Inference: Rediscovering the Role of Natural Language Inference for Large Language Models](https://mlsanity.com/paper/2411.14103/) (2024)
- [AutoSurvey2: Empowering Researchers with Next Level Automated Literature Surveys](https://mlsanity.com/paper/2510.26012/) (2025)
- [Agentic AutoSurvey: Let LLMs Survey LLMs](https://mlsanity.com/paper/2509.18661/) (2025)
- [LLM×MapReduce-V2: Entropy-Driven Convolutional Test-Time Scaling for Generating Long-Form Articles from Extremely Long Resources](https://mlsanity.com/paper/2504.05732/) (2025)

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

- [Making AI Scientists Auditable from Evidence to Claim](https://mlsanity.com/paper/2606.18874/) (2026)

## Abstract (arXiv)

As scientific literature grows rapidly and research increasingly involves AI agents, automated survey generation has become a key capability for both agents and human researchers. For such agents, a survey serves as a primary knowledge source of a field prior to research. Since pretrained models already encode broad knowledge of established work, these consumers benefit more from analytical depth than from breadth alone; moreover, unsupported claims, once ingested as knowledge, can propagate into downstream research. However, existing systems tend to overemphasize coverage and presentation; they suffer from limited analytical depth due to reliance on abstracts and isolated paper processing, and from unreliable citations due to imprecise retrieval and post-hoc grounding. We present DeepSurvey, an agentic generation system that addresses both limitations. To enhance depth, DeepSurvey extracts structured keynotes, models cross-paper relationships through clustering and comparative analysis, and integrates a code-agent subsystem to recover implementation-level details. To fortify reliability, it combines citation-graph expansion with hybrid filtering for topic-focused retrieval, enforces evidence-constrained analysis and writing, and deploys multi-granularity agentic refinement to validate citation--claim alignment. Experiments show that DeepSurvey achieves the highest content score (8.34/10) and citation quality (recall and precision gains of 25.3% and 35.2% over the strongest baseline), generalizes more robustly across domains, and is preferred by domain experts over human-written surveys (83.3% in overall quality, 100% in content depth). Moreover, when a coding agent uses a survey as its only literature source, the agent equipped with DeepSurvey achieves the best performance among human-written and baseline-generated surveys.