# BibAgent: An Agentic Framework for Traceable Miscitation Detection in Scientific Literature

arXiv: https://arxiv.org/abs/2601.16993 · HTML: https://mlsanity.com/paper/2601.16993/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 47 references that are in the map.
- First posted on arXiv 12 Jan 2026.

## Builds on (most cited first, 14 of 14)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities](https://mlsanity.com/paper/2507.06261/) (2025)
- [Fact or Fiction: Verifying Scientific Claims](https://mlsanity.com/paper/2004.14974/) (2020)
- [Simple synthetic data reduces sycophancy in large language models](https://mlsanity.com/paper/2308.03958/) (2023)
- [Mapping the Increasing Use of LLMs in Scientific Papers](https://mlsanity.com/paper/2404.01268/) (2024)
- [CiteME: Can Language Models Accurately Cite Scientific Claims?](https://mlsanity.com/paper/2407.12861/) (2024)
- [A Paragraph-level Multi-task Learning Model for Scientific Fact-Verification](https://mlsanity.com/paper/2012.14500/) (2020)
- [Detecting LLM-Generated Peer Reviews](https://mlsanity.com/paper/2503.15772/) (2025)
- [Overview and Insights from the SciVer Shared Task on Scientific Claim Verification](https://mlsanity.com/paper/2107.08188/) (2021)
- [A review of the literature on citation impact indicators](https://mlsanity.com/paper/1507.02099/) (2015)
- [VeriCite: Towards Reliable Citations in Retrieval-Augmented Generation via Rigorous Verification](https://mlsanity.com/paper/2510.11394/) (2025)
- [Detecting Reference Errors in Scientific Literature with Large Language Models](https://mlsanity.com/paper/2411.06101/) (2024)
- [Incidental or influential? - Challenges in automatically detecting citation importance using publication full texts](https://mlsanity.com/paper/1707.04207/) (2017)

## Built on by (most cited first, 9 of 9)

- [LLM hallucinations in the wild: Large-scale evidence from non-existent citations](https://mlsanity.com/paper/2605.07723/) (2026)
- [Detecting and Correcting Reference Hallucinations in Commercial LLMs and Deep Research Agents](https://mlsanity.com/paper/2604.03173/) (2026)
- [Let the Abyss Stare Back Adaptive Falsification for Autonomous Scientific Discovery](https://mlsanity.com/paper/2603.29045/) (2026)
- [CAPS: Cascaded Adaptive Pairwise Selection for Efficient Parallel Reasoning](https://mlsanity.com/paper/2605.15513/) (2026)
- [BibTeX Citation Errors in Scientific Publishing Agents: Evaluation and Mitigation](https://mlsanity.com/paper/2604.03159/) (2026)
- [AdaptFuse: Training-Free Sequential Preference Inference via Externalized Bayesian Computation](https://mlsanity.com/paper/2604.03925/) (2026)
- [PathCal: State-Aware Reflection-Marker Calibration for Efficient Reasoning](https://mlsanity.com/paper/2605.23074/) (2026)
- [Scientific exploration, collaboration and labor division in the large language model era](https://mlsanity.com/paper/2607.20923/) (2026)
- [How Is Automated Research Evaluated? A Survey of Benchmarks and Evaluation Practices](https://mlsanity.com/paper/2610.11877/) (2026)

## Abstract (arXiv)

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.