SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing

• URL: http://arxiv.org/abs/2508.14317v1
• Date: Wed, 20 Aug 2025 00:03:46 GMT
• Title: SurveyGen-I: Consistent Scientific Survey Generation with Evolving Plans and Memory-Guided Writing
• Authors: Jing Chen, Zhiheng Yang, Yixian Shen, Jie Liu, Adam Belloum, Chrysa Papagainni, Paola Grosso,
• Abstract summary: SurveyGen-I is an automatic survey generation framework that combines coarse-to-fine retrieval, adaptive planning, and memory-guided generation.<n> Experiments across four scientific domains demonstrate that SurveyGen-I consistently outperforms previous works in content quality, consistency, and citation coverage.
• Score: 4.1851807186568735
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Survey papers play a critical role in scientific communication by consolidating progress across a field. Recent advances in Large Language Models (LLMs) offer a promising solution by automating key steps in the survey-generation pipeline, such as retrieval, structuring, and summarization. However, existing LLM-based approaches often struggle with maintaining coherence across long, multi-section surveys and providing comprehensive citation coverage. To address these limitations, we introduce SurveyGen-I, an automatic survey generation framework that combines coarse-to-fine retrieval, adaptive planning, and memory-guided generation. SurveyGen-I first performs survey-level retrieval to construct the initial outline and writing plan, and then dynamically refines both during generation through a memory mechanism that stores previously written content and terminology, ensuring coherence across subsections. When the system detects insufficient context, it triggers fine-grained subsection-level retrieval. During generation, SurveyGen-I leverages this memory mechanism to maintain coherence across subsections. Experiments across four scientific domains demonstrate that SurveyGen-I consistently outperforms previous works in content quality, consistency, and citation coverage.

Related papers

• DeepSynth-Eval: Objectively Evaluating Information Consolidation in Deep Survey Writing [53.85037373860246]
  We introduce Deep Synth-Eval, a benchmark designed to objectively evaluate information consolidation capabilities.<n>We propose a fine-grained evaluation protocol using General Checklists (for factual coverage) and Constraint Checklists (for structural organization)<n>Our results demonstrate that agentic plan-and-write significantly outperform single-turn generation.
  arXiv  Detail & Related papers  (2026-01-07T03:07:52Z)
• Deep Literature Survey Automation with an Iterative Workflow [30.923568155892184]
  ours is a framework based on recurrent outline generation to ensure both exploration and coherence.<n>To provide faithful paper-level grounding, we design paper cards that distill each paper into its contributions, methods, and findings.<n>Experiments on both established and emerging topics show that ours substantially outperforms state-of-the-art baselines in content coverage, structural coherence, and citation quality.
  arXiv  Detail & Related papers  (2025-10-24T14:41:26Z)
• SurveyG: A Multi-Agent LLM Framework with Hierarchical Citation Graph for Automated Survey Generation [4.512335376984058]
  Large language models (LLMs) are increasingly adopted for automating survey paper generation.<n>We propose textbfSurveyG, an LLM-based agent framework that integrates textithierarchical citation graph<n>The graph is organized into three layers: textbfFoundation, textbfDevelopment, and textbfFrontier, to capture the evolution of research from seminal works to incremental advances and emerging directions.
  arXiv  Detail & Related papers  (2025-10-09T03:14:20Z)
• Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches [6.740646039135986]
  Retrieval-Augmented Generation (RAG) has emerged as a powerful paradigm that integrates external retrieval mechanisms with LLMs.<n>We provide a comprehensive review of research on Retrieval-Augmented Code Generation (RACG), with an emphasis on repository-level approaches.<n>Our goal is to establish a unified analytical framework for understanding this rapidly evolving field and to inspire continued progress in AI-powered software engineering.
  arXiv  Detail & Related papers  (2025-10-06T15:20:03Z)
• SurGE: A Benchmark and Evaluation Framework for Scientific Survey Generation [37.921524136479825]
  SurGE (Survey Generation Evaluation) is a new benchmark for scientific survey generation in computer science.<n>SurGE consists of (1) a collection of test instances, each including a topic description, an expert-written survey, and its full set of cited references, and (2) a large-scale academic corpus of over one million papers.<n>In addition, we propose an automated evaluation framework that measures the quality of generated surveys across four dimensions.
  arXiv  Detail & Related papers  (2025-08-21T15:45:10Z)
• A Survey on Parallel Text Generation: From Parallel Decoding to Diffusion Language Models [49.97547209846335]
  parallel text generation techniques aimed at breaking the token-by-token generation bottleneck and improving inference efficiency.<n>We categorize existing approaches into AR-based and Non-AR-based paradigms, and provide a detailed examination of the core techniques within each category.<n>We highlight recent advancements, identify open challenges, and outline promising directions for future research in parallel text generation.
  arXiv  Detail & Related papers  (2025-08-12T07:56:04Z)
• SurveyForge: On the Outline Heuristics, Memory-Driven Generation, and Multi-dimensional Evaluation for Automated Survey Writing [13.101632066188532]
  We introduce SurveyForge, which generates the outline by analyzing the logical structure of human-written outlines.<n>To achieve a comprehensive evaluation, we construct SurveyBench, which includes 100 human-written survey papers for win-rate comparison.<n>Experiments demonstrate that SurveyForge can outperform previous works such as AutoSurvey.
  arXiv  Detail & Related papers  (2025-03-06T17:15:48Z)
• TrustRAG: An Information Assistant with Retrieval Augmented Generation [73.84864898280719]
  TrustRAG is a novel framework that enhances acRAG from three perspectives: indexing, retrieval, and generation.<n>We open-source the TrustRAG framework and provide a demonstration studio designed for excerpt-based question answering tasks.
  arXiv  Detail & Related papers  (2025-02-19T13:45:27Z)
• Chain-of-Retrieval Augmented Generation [91.02950964802454]
  This paper introduces an approach for training o1-like RAG models that retrieve and reason over relevant information step by step before generating the final answer.<n>Our proposed method, CoRAG, allows the model to dynamically reformulate the query based on the evolving state.
  arXiv  Detail & Related papers  (2025-01-24T09:12:52Z)
• ConTReGen: Context-driven Tree-structured Retrieval for Open-domain Long-form Text Generation [26.4086456393314]
  Long-form text generation requires coherent, comprehensive responses that address complex queries with both breadth and depth. Existing iterative retrieval-augmented generation approaches often struggle to delve deeply into each facet of complex queries. This paper introduces ConTReGen, a novel framework that employs a context-driven, tree-structured retrieval approach.
  arXiv  Detail & Related papers  (2024-10-20T21:17:05Z)
• Taxonomy Tree Generation from Citation Graph [15.188580557890942]
  HiGTL is a novel end-to-end framework guided by human-provided instructions or preferred topics.<n>We develop a novel taxonomy node verbalization strategy that iteratively generates central concepts for each cluster.<n>Experiments demonstrate that HiGTL effectively produces coherent, high-quality concept.
  arXiv  Detail & Related papers  (2024-10-02T13:02:03Z)
• Ground Every Sentence: Improving Retrieval-Augmented LLMs with Interleaved Reference-Claim Generation [51.8188846284153]
  Attributed Text Generation (ATG) is proposed to enhance credibility and verifiability in RAG systems.<n>This paper proposes ReClaim, a fine-grained ATG method that alternates the generation of references and answers step by step.<n>With extensive experiments, we verify the effectiveness of ReClaim in extensive settings, achieving a citation accuracy rate of 90%.
  arXiv  Detail & Related papers  (2024-07-01T20:47:47Z)
• From Matching to Generation: A Survey on Generative Information Retrieval [21.56093567336119]
  This paper systematically reviews the latest research progress in generative information retrieval (GenIR)<n>We will summarize the advancements in GR regarding model training and structure, document identifier, incremental learning, etc.<n>We also review the evaluation, challenges and future developments in GenIR systems.
  arXiv  Detail & Related papers  (2024-04-23T09:05:37Z)
• A Survey on Retrieval-Augmented Text Generation [53.04991859796971]
  Retrieval-augmented text generation has remarkable advantages and has achieved state-of-the-art performance in many NLP tasks. It firstly highlights the generic paradigm of retrieval-augmented generation, and then it reviews notable approaches according to different tasks.
  arXiv  Detail & Related papers  (2022-02-02T16:18:41Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.