Related papers: paper.json: A Coordination Convention for LLM-Agen…

Correctly parsing mathematical formulas from PDFs is critical for training large language models and building scientific knowledge bases from academic literature, yet existing benchmarks either exclude formulas entirely or lack…

Scientific literature contain important information related to cutting-edge innovations in diverse domains. Advances in natural language processing have been driving the fast development in automated information extraction from scientific…

Verifying mathematical proofs is difficult, but can be automated with the assistance of a computer. Autoformalization is the task of automatically translating natural language mathematics into a formal language that can be verified by a…

Operating LLMs as coordinated multi-agent research systems over multi-hour runs surfaces failure modes that single-shot evaluation cannot: upstream providers throttle without warning, sub-agents drift the task to fit accessible tools,…

LLM-generated explanations can make technical content more accessible, but there is a ceiling on what they can support interactively. Because LLM outputs are static text, they cannot be executed or stepped through. We argue that grounding…

Large language models (LLMs) are increasingly used to generate requirements specifications, design documents, code, and test cases. In contrast, much less attention has been given to a more difficult assurance problem: statically verifying…

One type of machine learning, text classification, is now regularly applied in the legal matters involving voluminous document populations because it can reduce the time and expense associated with the review of those documents. One form of…

Research papers are well structured documents. They have text, figures, equations, tables etc., to covey their ideas and findings. They are divided into sections like Introduction, Model, Experiments etc., which deal with different aspects…

Science and engineering research increasingly relies on activities that facilitate research but are not currently rewarded or recognized, such as: data sharing; developing common data resources, software and methodologies; and annotating…

Software documentation frequently becomes outdated or fails to exist entirely, yet developers need focused views of their codebase to understand complex systems. While automated reverse engineering tools can generate UML diagrams from code,…

We introduce TableLLM, a robust large language model (LLM) with 8 billion parameters, purpose-built for proficiently handling tabular data manipulation tasks, whether they are embedded within documents or spreadsheets, catering to…

Process mining assumes the existence of an event log where each event refers to a case, an activity, and a point in time. XES is an XML based IEEE approved standard format for event logs supported by most of the process mining tools. JSON…

Verifying LLM-generated systems code is hard: bugs are prevalent, formal specifications are missing, and safety contracts are encoded implicitly at call sites rather than enforced at function boundaries. We propose agentic model checking, a…

In recent years, the research focus of large language models (LLMs) and agents has shifted increasingly from demonstrating novel capabilities to complex reasoning and tackling challenging tasks. However, existing evaluations focus mainly on…

We introduce LongDA, a data analysis benchmark for evaluating LLM-based agents under documentation-intensive analytical workflows. In contrast to existing benchmarks that assume well-specified schemas and inputs, LongDA targets real-world…

Large language models (LLMs) have shown impressive performance on general-purpose tasks, yet adapting them to specific domains remains challenging due to the scarcity of high-quality domain data. Existing data synthesis tools often struggle…

Computer use agents (CUA) are systems that automatically interact with graphical user interfaces (GUIs) to complete tasks. CUA have made significant progress with the advent of large vision-language models (VLMs). However, these agents…

The explosive growth of AI research has driven paper submissions at flagship AI conferences to unprecedented levels, necessitating many venues in 2025 (e.g., CVPR, ICCV, KDD, AAAI, IJCAI, WSDM) to enforce strict per-author submission limits…

A naive realization of JSON data in R maps JSON arrays to an unnamed list, and JSON objects to a named list. However, in practice a list is an awkward, inefficient type to store and manipulate data. Most statistical applications work with…

Leveraging large language models (LLMs) to generate high-stakes documents, such as informed consent forms (ICFs), remains a significant challenge due to the extreme need for regulatory compliance and factual accuracy. Here, we present…