BRIGHT+: Upgrading the BRIGHT Benchmark with MARCUS, a Multi-Agent RAG Clean-Up Suite
Liyang Chen, Yujun Cai, Jieqiong Dong, Yiwei Wang

TL;DR
This paper introduces MARCUS, a multi-agent system that enhances the BRIGHT benchmark by cleaning and restructuring its corpus, leading to better retrieval accuracy and reasoning performance in RAG systems.
Contribution
The paper presents MARCUS, a novel multi-agent pipeline that systematically improves the quality of the BRIGHT benchmark corpus, addressing web-crawled artifacts and enhancing its utility for complex retrieval tasks.
Findings
BRIGHT-Plus improves retrieval accuracy across multiple retrievers.
Enhanced corpus leads to better multi-hop reasoning performance.
MARCUS effectively removes structural noise and semantic discontinuities.
Abstract
Retrieval-Augmented Generation (RAG) systems require corpora that are both structurally clean and semantically coherent. BRIGHT is a recent and influential benchmark designed to evaluate complex multi-hop retrieval across diverse, high-reasoning domains. However, its practical effectiveness is limited by common web-crawled artifacts - such as content redundancy and semantic discontinuity - that impair retrieval accuracy and downstream reasoning. Notably, we find that such issues are concentrated in seven StackExchange-derived subdomains, while other domains (e.g., Coding and Theorem-based content) remain relatively clean. In this study, we present MARCUS, a multi-agent pipeline that leverages large language models (LLMs) to systematically clean and re-chunk BRIGHT into a higher-quality corpus: BRIGHT-Plus. MARCUS applies dedicated agents for structural noise removal and semantic…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsInformation Retrieval and Search Behavior · Topic Modeling · Multimodal Machine Learning Applications
