Related papers: IDP Accelerator: Agentic Document Intelligence fro…
Materials language processing (MLP) is one of the key facilitators of materials science research, as it enables the extraction of structured information from massive materials science literature. Prior works suggested high-performance MLP…
We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents…
Understanding the contents of multimodal documents is essential to accurately extract relevant evidence and use it for reasoning. Existing document understanding models tend to generate answers with a single word or phrase directly,…
Building and deploying machine learning solutions in healthcare remains expensive and labor-intensive due to fragmented preprocessing workflows, model compatibility issues, and stringent data privacy constraints. In this work, we introduce…
Applying reinforcement learning (RL) to real-world tasks requires converting informal descriptions into a formal Markov decision process (MDP), implementing an executable environment, and training a policy agent. Automating this process is…
While Large Language Models (LLMs) demonstrate remarkable proficiency in semantic understanding, they often struggle to ensure structural consistency and reasoning reliability in complex decision-making tasks that demand rigorous logic.…
The large set of technical documentation of legacy accelerator systems, coupled with the retirement of experienced personnel, underscores the urgent need for efficient methods to preserve and transfer specialized knowledge. This paper…
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,…
Automated machine learning (AutoML) accelerates AI development by automating tasks in the development pipeline, such as optimal model search and hyperparameter tuning. Existing AutoML systems often require technical expertise to set up…
Document understanding in real-world applications often requires processing heterogeneous, multi-page document packets containing multiple documents stitched together. Despite recent advances in visual document understanding, the…
Federated data processing (FDP) offers a promising approach for enabling collaborative analysis of sensitive data without centralizing raw datasets. However, real-world adoption remains limited due to the complexity of managing…
Large language models (LLMs), when guided by explicit textual plans, can perform reliable step-by-step reasoning during problem-solving. However, generating accurate and effective textual plans remains challenging due to LLM hallucinations…
Prompt engineering for LLMs remains complex, with existing frameworks either hiding complexity behind restrictive APIs or providing inflexible canned patterns that resist customization -- making sophisticated agentic programming…
Traditional control system design, reliant on expert knowledge and precise models, struggles with complex, nonlinear, or uncertain dynamics. This paper introduces AgenticControl, a novel multi-agent framework that automates controller…
Abstractive summarization is an ideal form of summarization since it can synthesize information from multiple documents to create concise informative summaries. In this work, we aim at developing an abstractive summarizer. First, our…
Information extraction from copy-heavy documents, characterized by massive volumes of structurally similar content, represents a critical yet understudied challenge in enterprise document processing. We present a systematic framework that…
Conformance testing is essential for ensuring that protocol implementations comply with their specifications. However, traditional testing approaches involve manually creating numerous test cases and scripts, making the process…
The rapidly growing demand for high-quality data in Large Language Models (LLMs) has intensified the need for scalable, reliable, and semantically rich data preparation pipelines. However, current practices remain dominated by ad-hoc…
Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…
Software development agents powered by large language models (LLMs) have shown great promise in automating tasks like environment setup, issue solving, and program repair. Unfortunately, understanding and debugging such agents remain…