Related papers: Spec-Driven AI for Science: The ARIA Framework for…
The exponential growth of academic publications poses challenges for the research process, such as literature review and procedural planning. Large Language Models (LLMs) have emerged as powerful AI tools, especially when combined with…
Developing effective, domain-specific educational support systems is central to advancing AI in education. Although large language models (LLMs) demonstrate remarkable capabilities, they face significant limitations in specialized…
Accurate auto-formalization of theorem statements is essential for advancing automated discovery and verification of research-level mathematics, yet remains a major bottleneck for LLMs due to hallucinations, semantic mismatches, and their…
Artificial intelligence (AI) tools are being incorporated into scientific research workflows with the potential to enhance efficiency in tasks such as document analysis, question answering (Q&A), and literature search. However, system…
Information comes in diverse modalities. Multimodal native AI models are essential to integrate real-world information and deliver comprehensive understanding. While proprietary multimodal native models exist, their lack of openness imposes…
The integration of Artificial Intelligence (AI) into high-stakes domains such as healthcare, finance, and autonomous systems is often constrained by concerns over transparency, interpretability, and trust. While Human-Centered AI (HCAI)…
Existing automated research systems operate as stateless, linear pipelines -- generating outputs without maintaining any persistent understanding of the research landscape they navigate. They process papers sequentially, propose ideas…
The cycle of scientific discovery is frequently bottlenecked by the slow, manual creation of software to support computational experiments\cite{hannay2009how}. To address this, we present Empirical Research Assistance (ERA), an AI system…
Scientific research is being reshaped by AI systems that move beyond isolated assistance toward longer-horizon workflows spanning literature grounding, hypothesis generation, experimentation, validation, reporting, and revision. This shift…
Scientific peer review increasingly struggles to assess reproducibility at the scale and complexity of modern research output. Evaluating reproducibility requires reconstructing experimental dependencies, methodological choices, data flows,…
A growing trend in modern data analysis is the integration of data management with learning, guided by accuracy, latency, and cost requirements. In practice, applications draw data of different formats from many sources. In the meanwhile,…
In recent years, several personalized assistants based on AI have been researched and developed to help users make privacy-related decisions. These AI-driven Personalized Privacy Assistants (AI-driven PPAs) can provide significant benefits…
Large language model (LLM) agents often struggle in environments where rules and required domain knowledge frequently change, such as regulatory compliance and user risk screening. Current approaches, like offline fine-tuning and standard…
AI-assisted research is crossing a threshold: fully automated systems can now generate research papers for as little as $15, while long-horizon agents can execute experiments, draft manuscripts, and simulate critique with minimal human…
Data annotation is essential for supervised learning, yet producing accurate, unbiased, and scalable labels remains challenging as datasets grow in size and modality. Traditional human-centric pipelines are costly, slow, and prone to…
Artificial intelligence is reshaping science and industry, yet many users still regard its models as opaque "black boxes". Conventional explainable artificial-intelligence methods clarify individual predictions but overlook the upstream…
As autonomous agentic AI systems see increasing adoption across organisations, persistent challenges in alignment, governance, and risk management threaten to impede deployment at scale. We present AURA (Agent aUtonomy Risk Assessment), a…
We introduce Meta Agents Research Environments (ARE), a research platform for scalable creation of environments, integration of synthetic or real applications, and execution of agentic orchestrations. ARE provides simple abstractions to…
Document Visual Question Answering (VQA) requires models to not only extract accurate textual answers but also precisely localize them within document images, a capability critical for interpretability in high-stakes applications. However,…
This paper describes MAIA, a Multimodal Automated Interpretability Agent. MAIA is a system that uses neural models to automate neural model understanding tasks like feature interpretation and failure mode discovery. It equips a pre-trained…