Structure-Guided Memory Consolidation for Mitigating Compounding Errors in Literature Review Generation

TL;DR

This paper introduces Structure-Guided Memory Consolidation (SGMC), a framework that reduces error propagation in automatic literature review generation by using structured representations and multiple memory modules.

Contribution

The paper presents a novel SGMC framework with three modules that enhance information verification and consolidation in literature review generation, addressing error accumulation issues.

Findings

Achieves state-of-the-art citation accuracy

Significantly reduces error propagation in reviews

Improves content quality in long-form generation

Abstract

Compounding errors pose a significant challenge in automatic literature review generation, as inaccuracies can cascade across multi-stage retrieval and generation workflows. Existing self-correction strategies often lack mechanisms to effectively track and consolidate verified information throughout the process, making it difficult to prevent error accumulation and propagation. In this paper, we propose Structure-Guided Memory Consolidation (SGMC), a novel framework that incrementally consolidates and verifies information using structured representations at each stage of the literature review pipeline. SGMC consists of three key modules: Tree-Guided Memory for hierarchical literature retrieval and outline generation, Hub-Guided Memory for evidence extraction and iterative content refinement, and Self-Loop Memory for proactive error correction via historical feedback. Extensive experiments on public benchmarks and a newly constructed large-scale dataset demonstrate that SGMC achieves state-of-the-art performance in citation accuracy and content quality, significantly mitigating compounding errors in long-form literature review generation.