# SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?

arXiv: https://arxiv.org/abs/2510.03120 · HTML: https://mlsanity.com/paper/2510.03120/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 10 references that are in the map.
- First posted on arXiv 3 Oct 2025.

## Builds on (most cited first, 8 of 8)

- [Retrieval-Augmented Generation for Large Language Models: A Survey](https://mlsanity.com/paper/2312.10997/) (2023)
- [DeepResearch Bench: A Comprehensive Benchmark for Deep Research Agents](https://mlsanity.com/paper/2506.11763/) (2025)
- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [AutoSurvey: Large Language Models Can Automatically Write Surveys](https://mlsanity.com/paper/2406.10252/) (2024)
- [Vision-Language-Action (VLA) Models: Concepts, Progress, Applications and Challenges](https://mlsanity.com/paper/2505.04769/) (2025)
- [SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing](https://mlsanity.com/paper/2503.04629/) (2025)
- [SurveyX: Academic Survey Automation via Large Language Models](https://mlsanity.com/paper/2502.14776/) (2025)

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

- [AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents](https://mlsanity.com/paper/2602.06855/) (2026)
- [Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomies](https://mlsanity.com/paper/2601.12369/) (2026)
- [SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generation](https://mlsanity.com/paper/2602.11238/) (2026)
- [Making AI Scientists Auditable from Evidence to Claim](https://mlsanity.com/paper/2606.18874/) (2026)
- [How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices](https://mlsanity.com/paper/2610.11877/) (2026)

## Abstract (arXiv)

Academic survey writing, which distills vast literature into a coherent and insightful narrative, remains a labor-intensive and intellectually demanding task. While recent approaches, such as general DeepResearch agents and survey-specialized methods, can generate surveys automatically (a.k.a. LLM4Survey), their outputs often fall short of human standards and there lacks a rigorous, reader-aligned benchmark for thoroughly revealing their deficiencies. To fill the gap, we propose a fine-grained, quiz-driven evaluation framework SurveyBench, featuring (1) typical survey topics source from recent 11,343 arXiv papers and corresponding 4,947 high-quality surveys; (2) a multifaceted metric hierarchy that assesses the outline quality (e.g., coverage breadth, logical coherence), content quality (e.g., synthesis granularity, clarity of insights), and non-textual richness; and (3) a dual-mode evaluation protocol that includes content-based and quiz-based answerability tests, explicitly aligned with readers' informational needs. Results show SurveyBench effectively challenges existing LLM4Survey approaches (e.g., on average 21% lower than human in content-based evaluation).