InteractiveSurvey: An LLM-based Personalized and Interactive Survey Paper Generation System

arXiv 2025 44.6 method

TLDR

InteractiveSurvey is an LLM-based system for generating personalized, interactive survey papers with user customization and high quality.

Reasoning

The paper introduces a novel interactive survey generation system that allows user customization of intermediate components, which is a strength. However, its scope is limited to survey paper generation and does not address broader automated scientific discovery or experimentation. The evaluation includes user studies and quality metrics, supporting its claims.

Read-first score

Read-first score 44.6, weighted from topical fit, citation, graph, method, reproducibility, and recency signals. Original total remains 50.

Recency 8%

86.7

Uses a gentle age decay so recent papers surface without erasing older foundations. 2025

Methodology quality 25%

Screens visible abstract and analysis fields for experiment, dataset, baseline, metric, and limitation evidence. markers=evaluation

Topical relevance 42%

41.7

Uses existing LLM keyword relevance scores normalized to 0-100. AI scientist,automated scientific discovery,autonomous research agent,automated research,literature review agent,survey generation,automated experimentation,experiment design agent,AI for scientific research,paper writing agent,research automation,scientific discovery agent

Reproducibility 25%

Screens links and visible text for paper, code, dataset, artifact, and repository signals. pdf=True; code=False; dataset=False; markers=none

Field roles

Frontier

Rank sensitivity

Stability: volatile; rank range: 67.

Keyword Scores

survey generation

literature review agent

paper writing agent

research automation

AI for scientific research

automated research

automated scientific discovery

scientific discovery agent

AI scientist

autonomous research agent

automated experimentation

experiment design agent

Deep Analysis

Innovations

Personalized and interactive survey generation allowing users to customize and refine intermediate components (reference categorization, outline, content) continuously.
Integration of both online retrieval and user uploads for reference collection.
Generation of structured, multi-modal survey papers with reference categorizations.
Intuitive interface for iterative refinement during the generation process.

Methodology

InteractiveSurvey leverages large language models and retrieval-augmented generation to synthesize survey papers from references gathered via online retrieval and user uploads. Users interactively customize reference categorization, outline, and content through an interface, with evaluations covering content quality, time efficiency, and user studies against LLMs and existing methods.

Key Results

InteractiveSurvey outperforms most LLMs and existing methods in output content quality while remaining highly time-efficient, as demonstrated by content quality, time efficiency, and user study evaluations.

Resources

Paper