BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866912861098344448 |
|---|---|
| author | Li, Peiran Lin, Fangzhou Xing, Shuo Zheng, Xiang Hong, Xi Yang, Siyuan Sun, Jiashuo Tu, Zhengzhong Ni, Chaoqun |
| author_facet | Li, Peiran Lin, Fangzhou Xing, Shuo Zheng, Xiang Hong, Xi Yang, Siyuan Sun, Jiashuo Tu, Zhengzhong Ni, Chaoqun |
| contents | Citations are the bedrock of scientific authority, yet their integrity is compromised by widespread miscitations: ranging from nuanced distortions to fabricated references. Systematic citation verification is currently unfeasible; manual review cannot scale to modern publishing volumes, while existing automated tools are restricted by abstract-only analysis or small-scale, domain-specific datasets in part due to the "paywall barrier" of full-text access. We introduce BibAgent, a scalable, end-to-end agentic framework for automated citation verification. BibAgent integrates retrieval, reasoning, and adaptive evidence aggregation, applying distinct strategies for accessible and paywalled sources. For paywalled references, it leverages a novel Evidence Committee mechanism that infers citation validity via downstream citation consensus. To support systematic evaluation, we contribute a 5-category Miscitation Taxonomy and MisciteBench, a massive cross-disciplinary benchmark comprising 6,350 miscitation samples spanning 254 fields. Our results demonstrate that BibAgent outperforms state-of-the-art Large Language Model (LLM) baselines in citation verification accuracy and interpretability, providing scalable, transparent detection of citation misalignments across the scientific literature. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_16993 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature Li, Peiran Lin, Fangzhou Xing, Shuo Zheng, Xiang Hong, Xi Yang, Siyuan Sun, Jiashuo Tu, Zhengzhong Ni, Chaoqun Digital Libraries Artificial Intelligence Citations are the bedrock of scientific authority, yet their integrity is compromised by widespread miscitations: ranging from nuanced distortions to fabricated references. Systematic citation verification is currently unfeasible; manual review cannot scale to modern publishing volumes, while existing automated tools are restricted by abstract-only analysis or small-scale, domain-specific datasets in part due to the "paywall barrier" of full-text access. We introduce BibAgent, a scalable, end-to-end agentic framework for automated citation verification. BibAgent integrates retrieval, reasoning, and adaptive evidence aggregation, applying distinct strategies for accessible and paywalled sources. For paywalled references, it leverages a novel Evidence Committee mechanism that infers citation validity via downstream citation consensus. To support systematic evaluation, we contribute a 5-category Miscitation Taxonomy and MisciteBench, a massive cross-disciplinary benchmark comprising 6,350 miscitation samples spanning 254 fields. Our results demonstrate that BibAgent outperforms state-of-the-art Large Language Model (LLM) baselines in citation verification accuracy and interpretability, providing scalable, transparent detection of citation misalignments across the scientific literature. |
| title | BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature |
| topic | Digital Libraries Artificial Intelligence |
| url | https://arxiv.org/abs/2601.16993 |