Related papers: BibAgent: An Agentic Framework for Traceable Misci…

Recent advances in Large Language Models (LLMs) have raised urgent concerns about LLM-generated text authenticity, prompting regulatory demands for reliable identification mechanisms. Although watermarking offers a promising solution,…

Extractive reading comprehension systems are designed to locate the correct answer to a question within a given text. However, a persistent challenge lies in ensuring these models maintain high accuracy in answering questions while reliably…

Language models are known to hallucinate incorrect information, and it is unclear if they are sufficiently accurate and reliable for use in scientific research. We developed a rigorous human-AI comparison methodology to evaluate language…

Recovering accurate architecture from large-scale legacy software is hindered by architectural drift, missing relations, and the limited context of Large Language Models (LLMs). We present ArchAgent, a scalable agent-based framework that…

Recent multimodal LLMs have shown promise in chart-based visual question answering, but their performance declines sharply on unannotated charts-those requiring precise visual interpretation rather than relying on textual shortcuts. To…

Automated interpretability systems aim to reduce the need for human labor and scale analysis to increasingly large models and diverse tasks. Recent efforts toward this goal leverage large language models (LLMs) at increasing levels of…

High-quality code documentation is crucial for software development especially in the era of AI. However, generating it automatically using Large Language Models (LLMs) remains challenging, as existing approaches often produce incomplete,…

Language agents increasingly act as web-enabled systems that search, browse, and synthesize information from diverse sources. However, these sources can include unreliable or adversarial content, and the robustness of agents to adversarial…

Large Language Models (LLMs) increasingly serve as research assistants, yet their reliability in scholarly tasks remains under-evaluated. In this work, we introduce PaperAsk, a benchmark that systematically evaluates LLMs across four key…

Large language models (LLMs) have grown in their usage to provide support for question answering across numerous disciplines. The models on their own have already shown promise for answering basic questions, however fail quickly where…

Author Name Disambiguation (AND) is a long-standing challenge in bibliometrics and scientometrics, as name ambiguity undermines the accuracy of bibliographic databases and the reliability of research evaluation. This study addresses the…

Despite recent advances in diffusion models, AI generated images still often contain visual artifacts that compromise realism. Although more thorough pre-training and bigger models might reduce artifacts, there is no assurance that they can…

This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark contains curated end-to-end tasks (e.g.,…

Mining software repositories often requires classifying artifacts like commits, reviews, code lines, or entire repositories into categories. Human labeling is expensive and error-prone; limited context frequently leads to misclassifications…

With the rapid progress of large language models (LLMs), LLM-powered multi-agent systems (MAS) are drawing increasing interest across academia and industry. However, many current MAS frameworks struggle with reliability and scalability,…

Recent agentic systems demonstrate that large language models can generate scientific visualizations from natural language. However, reliability remains a major limitation: systems may execute invalid operations, introduce subtle but…

As benchmarks grow in complexity, many apparent agent failures are not failures of the agent at all - they are failures of the benchmark itself: broken specifications, implicit assumptions, and rigid evaluation scripts that penalize valid…

Real-world design documents (e.g., posters) are inherently multi-layered, combining decoration, text, and images. Editing them from natural-language instructions requires fine-grained, layer-aware reasoning to identify relevant layers and…

The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped,…

The increasing prevalence of large language models (LLMs) has significantly advanced text generation, but the human-like quality of LLM outputs presents major challenges in reliably distinguishing between human-authored and LLM-generated…