mlsanityData to 14 Oct 2026

SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing

arXiv 2503.04629 ↗First posted 6 Mar 2025cs.CLcited by 49

Not on the map. Why?

Cited by 22 in LLM agents and tool use, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Survey paper plays a crucial role in scientific research, especially given the rapid growth of research publications. Recently, researchers have begun using LLMs to automate survey generation for better efficiency. However, the quality gap between LLM-generated surveys and those written by human remains significant, particularly in terms of outline quality and citation accuracy. To close these gaps, we introduce SurveyForge, which first generates the outline by analyzing the logical structure of human-written outlines and referring to the retrieved domain-related articles. Subsequently, leveraging high-quality papers retrieved from memory by our scholar navigation agent, SurveyForge can automatically generate and refine the content of the generated article. Moreover, to achieve a comprehensive evaluation, we construct SurveyBench, which includes 100 human-written survey papers for win-rate comparison and assesses AI-generated survey papers across three dimensions: reference, outline, and content quality. Experiments demonstrate that SurveyForge can outperform previous works such as AutoSurvey.

Key facts. Cited by 49 papers in the map (data through 14 Oct 2026). Builds on 17 of its 32 references that are in the map. First posted on arXiv 6 Mar 2025.

Builds on

17 of 32 references.

References · 17

  1. 2023GPT-4 Technical Reportcited by 18,396
  2. 2023LLaMA: Open and Efficient Foundation Language Modelscited by 14,132
  3. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
  4. 2023Retrieval-Augmented Generation for Large Language Models: A Surveycited by 2,212
  5. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  6. 2024How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suitescited by 1,050
  7. 2023Towards General Text Embeddings with Multi-stage Contrastive Learningcited by 723
  8. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 366
  9. 2024MinerU: An Open-Source Solution for Precise Document Content Extractioncited by 267
  10. 2024ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discoverycited by 235
  11. 2024ChartX & ChartVLM: A Versatile Benchmark and Foundation Model for Complicated Chart Reasoningcited by 128
  12. 2024SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoningcited by 94
5 more
  1. 2024OpenScholar: Synthesizing Scientific Literature with Retrieval-augmented LMscited by 72
  2. 2024Nova: An Iterative Planning and Search Approach to Enhance Novelty and Diversity of LLM Generated Ideascited by 57
  3. 2024SciPIP: An LLM-based Scientific Paper Idea Proposercited by 26
  4. 2025Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedbackcited by 25
  5. 2023Hierarchical Catalogue Generation for Literature Review: A Benchmarkcited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 21; 2026: 28.

49 papers.

Sort:

By area:

  1. 2025KVCOMM: Online Cross-context KV-cache Communication for Efficient LLM-based Multi-agent Systemscited by 40
  2. 2025ReportBench: Evaluating Deep Research Agents via Academic Survey Taskscited by 38
  3. 2025A Survey of Scientific Large Language Models: From Data Foundations to Agent Frontierscited by 37
  4. 2025Ai2 Scholar QA: Organized Literature Synthesis with Attributioncited by 25
  5. 2025A Vision for Auto Research with LLM Agentscited by 18
  6. 2025SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generationcited by 16
  7. 2025SciSage: A Multi-Agent Framework for High-Quality Scientific Survey Generationcited by 12
  8. 2026AI for Auto-Research: Roadmap & User Guidecited by 11
  9. 2025Context-Aware Hierarchical Taxonomy Generation for Scientific Papers via LLM-Guided Multi-Aspect Clusteringcited by 10
  10. 2025SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generationcited by 10
  11. 2025Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluatorcited by 9
  12. 2026Autonomous Research Agents: A Survey of AI Scientists and the Verification Gapcited by 9
37 more
  1. 2025Stop DDoS Attacking the Research Community with AI-Generated Survey Paperscited by 7
  2. 2025Deep Literature Survey Automation with an Iterative Workflowcited by 7
  3. 2025SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writingcited by 5
  4. 2025SurveyBench: Can LLM(-Agents) Write Academic Surveys that Align with Reader Needs?cited by 5
  5. 2025Scaling External Knowledge Input Beyond Context Windows of LLMs via Multi-Agent Collaborationcited by 4
  6. 2026DeepSurvey-Bench: Evaluating Academic Value of Automatically Generated Scientific Surveyscited by 4
  7. 2026STRUCTSURVEY: Structured Agentic Retrieval for Automated Survey Paper Generationcited by 4
  8. 2025SGSimEval: A Comprehensive Multifaceted and Similarity-Enhanced Benchmark for Automatic Survey Generation Systemscited by 3
  9. 2025ARISE: Agentic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper Generationcited by 3
  10. 2026Can Deep Research Agents Retrieve and Organize? Evaluating the Synthesis Gap with Expert Taxonomiescited by 3
  11. 2026Agentic-Ideation: Sample Efficient Agentic Trajectories Synthesis for Scientific Ideation Agentscited by 3
  12. 2025TaxoAlign: Scholarly Taxonomy Generation Using Language Modelscited by 2
  13. 2026Agentic AI-Empowered Dynamic Survey Frameworkcited by 2
  14. 2026Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Userscited by 2
  15. 2025SurveyEval: Towards Comprehensive Evaluation of LLM-Generated Academic Surveyscited by 1
  16. 2025Eliminating Agentic Workflow for Introduction Generation with Parametric Stage Tokenscited by 1
  17. 2025HybridQuestion: Human-AI Collaboration for Identifying High-Impact Research Questionscited by 1
  18. 2026AgentCPM-Report: Interleaving Drafting and Deepening for Open-Ended Deep Researchcited by 1
  19. 2026SurveyLens: A Discipline-Aware Benchmark for Automatic Survey Generationcited by 1
  20. 2026DRACULA: Hunting for the Actions Users Want Deep Research Agents to Executecited by 1
  21. 2026SciAtlas: A Computable Atlas of Science for Knowledge-Grounded AI Researchcited by 1
  22. 2026Science Earth: Towards A Planet-Scale Operating System for AI-Native Scientific Discoverycited by 1
  23. 2026MVSS: A Unified Framework for Multi-View Structured Survey Generationcited by 0
  24. 2026OUTLINEFORGE: Hierarchical Reinforcement Learning with Explicit States for Scientific Writingcited by 0
  25. 2026Multi-Dimensional Knowledge Profiling with Large-Scale Literature Database and Hierarchical Retrievalcited by 0
  26. 2026AiraXiv: An AI-Driven Open-Access Platform for Human and AI Scientistscited by 0
  27. 2026LECTOR: Joint Optimization of Scientific Reasoning Graphs and Introduction Generationcited by 0
  28. 2026MetaSyn: A Benchmark for LLM Agents on Meta-Analysis Articles from Nature Portfoliocited by 0
  29. 2026Internalizing Academic Writing Workflows for Introduction Generation via Struct-Aware Policy Learningcited by 0
  30. 2026Deep Academic Survey: Stateful Agentic Closed-Loop Paradigm for Academic Survey Automationcited by 0
  31. 2026DeepWeaver: Bridging the Evidence Synthesis Gap in Open-Ended Question Answeringcited by 0
  32. 2026LitReview Arena: Evaluating Literature Review Agents with Battle-Style Peer Review Platformcited by 0
  33. 2026GRAFT: Graph-Distilled Generative Retrieval for Facet-Aware Scientific Literature Explorationcited by 0
  34. 2026SurveyAgent-HKA: A multi-agent framework for scientific survey generation with LLMs and human knowledge augmentationcited by 0
  35. 2026BizSage: A Self-Evolving Multi-Agent Framework for Business Research with Efficient Knowledge Retrievalcited by 0
  36. 2026What Can a Leaderboard Certify? Compositional Controllability for Fair Evaluation and Training of Biomedical Literature-Review Agentscited by 0
  37. 2026IdeaScientist: Orchestrating Agents for Grounded Scientific Ideationcited by 0