Research - Papers
Explore a selection of our published work on a variety of key research challenges in AI.
DR Tulu: Reinforcement Learning with Evolving Rubrics for Deep Research
Deep research agents perform multi-step research to produce long-form, well-attributed answers. However, most open deep research agents are trained on easily verifiable short-form QA tasks via…
Generating Literature-Driven Scientific Theories at Scale
Contemporary automated scientific discovery has focused on agents for generating scientific experiments, while systems that perform higher-level scientific activities such as theory building remain…
Language Models Don't Know What You Want: Evaluating Personalization in Deep Research Needs Real Users
Deep Research (DR) systems help researchers cope with ballooning publishing counts. Such tools synthesize scientific papers to answer research queries, but lack understanding of their users. We…
Evidence-Informed LLM Beliefs for Continual Scientific Discovery
Open-ended scientific discovery with large language models (LLMs) increasingly operates as a long-horizon loop of hypothesis search and verification, where a reward signal guides which hypotheses to…
Enabling federated discovery leveraging agentic AI systems: The Cancer AI Alliance and DataVoyager
Background: Artificial intelligence (AI) has the potential to transform oncology, but robust AI models require diverse, multi-institutional data that preserve patient privacy. Federating data across…
Scientific reasoning does not reliably translate into scientific forecasting in frontier AI
AI systems are increasingly used to support forward-looking scientific judgment, but it remains unclear whether they can form reliable expectations about future scientific advances. Here we show…
Distribution-Aware Reward: Reinforcement Learning over Predictive Distributions for LLM Regression
Large language models can predict real-valued quantities from heterogeneous inputs such as text, code, and molecular strings, but most training objectives score each decoded floating-point number…
Improving Attributed Long-form Question Answering with Intent Awareness
Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports. However, while these models are trained on diverse academic papers and reports, they…
DRACULA: Hunting for the Actions Users Want Deep Research Agents to Execute
Scientific Deep Research (DR) agents answer user queries by synthesizing research papers into multi-section reports. User feedback can improve their utility, but existing protocols only score the…
AstaBench: Rigorous Benchmarking of AI Agents with a Scientific Research Suite
AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed,…