ARISE: Agentic Rubric-Guided Iterative Survey Engine for Automated Scholarly Paper Generation

TL;DR

ARISE is an innovative system that automates scholarly survey paper generation through modular language model agents and iterative rubric-guided refinement, significantly improving quality and adaptability over existing solutions.

Contribution

This paper introduces ARISE, a novel agentic framework employing structured refinement loops and specialized agents for automated, high-quality scholarly survey generation.

Findings

Achieved an average rubric-aligned quality score of 92.48

Outperformed state-of-the-art automated systems and human surveys

Demonstrated improvements in comprehensiveness, accuracy, and formatting

Abstract

The rapid expansion of scholarly literature presents significant challenges in synthesizing comprehensive, high-quality academic surveys. Recent advancements in agentic systems offer considerable promise for automating tasks that traditionally require human expertise, including literature review, synthesis, and iterative refinement. However, existing automated survey-generation solutions often suffer from inadequate quality control, poor formatting, and limited adaptability to iterative feedback, which are core elements intrinsic to scholarly writing. To address these limitations, we introduce ARISE, an Agentic Rubric-guided Iterative Survey Engine designed for automated generation and continuous refinement of academic survey papers. ARISE employs a modular architecture composed of specialized large language model agents, each mirroring distinct scholarly roles such as topic expansion, citation curation, literature summarization, manuscript drafting, and peer-review-based evaluation. Central to ARISE is a rubric-guided iterative refinement loop in which multiple reviewer agents independently assess manuscript drafts using a structured, behaviorally anchored rubric, systematically enhancing the content through synthesized feedback. Evaluating ARISE against state-of-the-art automated systems and recent human-written surveys, our experimental results demonstrate superior performance, achieving an average rubric-aligned quality score of 92.48. ARISE consistently surpasses baseline methods across metrics of comprehensiveness, accuracy, formatting, and overall scholarly rigor. All code, evaluation rubrics, and generated outputs are provided openly at https://github.com/ziwang11112/ARISE