Related papers: CodeScientist: End-to-End Semi-Automated Scientifi…
Recent LLM-based agents have closed substantial portions of the scientific discovery loop in software-only machine-learning research, in chemistry, and in biology. Extending the same loop to high-fidelity physical simulators is harder,…
Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good agent-generated papers actually are. We introduce ResearchArena, a minimal…
Generative AI has the potential to transform knowledge work, but further research is needed to understand how knowledge workers envision using and interacting with generative AI. We investigate the development of generative AI tools to…
We present the AI Cosmologist, an agentic system designed to automate cosmological/astronomical data analysis and machine learning research workflows. This implements a complete pipeline from idea generation to experimental evaluation and…
Currently, data-intensive scientific applications require vast amounts of compute resources to deliver world-leading science. The climate emergency has made it clear that unlimited use of resources (e.g., energy) for scientific discovery is…
The dream of building machines that can do science has inspired scientists for decades. Remarkable advances have been made recently; however, we are still far from achieving this goal. In this paper, we focus on the scientific discovery…
A major challenge for niche scientific and technical domains in leveraging coding agents is the lack of access to up-to-date, domain- specific knowledge. Foundational models often demonstrate limited reasoning capabilities in specialized…
Recent advances in AI agents for software engineering and scientific discovery have demonstrated remarkable capabilities, yet their application to developing novel ranking models in commercial search engines remains unexplored. In this…
Keeping track of scientific challenges, advances and emerging directions is a fundamental part of research. However, researchers face a flood of papers that hinders discovery of important knowledge. In biomedicine, this directly impacts…
In this paper, we study a sequential decision-making problem, called Adaptive Sampling for Discovery (ASD). Starting with a large unlabeled dataset, algorithms for ASD adaptively label the points with the goal to maximize the sum of…
We present MOSAIC, a multi-agent Large Language Model (LLM) framework for solving challenging scientific coding tasks. Unlike general-purpose coding, scientific workflows require algorithms that are rigorous, interconnected with deep domain…
Scientific data processing often requires task-specific algorithms or AI models, creating a barrier for domain scientists who need to analyze their data but may not have extensive computing or image-processing expertise. This barrier is…
Foundation models have become general-purpose assistants, exhibiting diverse capabilities across numerous domains through training on web-scale data. It remains challenging to precisely characterize even a fraction of the full spectrum of…
Large Language Model (LLM)-based multi-agent systems (MAS) demonstrate remarkable potential for scientific discovery. Existing approaches, however, often automate scientific discovery using predefined workflows that lack rationality…
Given the remarkable performance of Large Language Models (LLMs), an important question arises: Can LLMs conduct human-like scientific research and discover new knowledge, and act as an AI scientist? Scientific discovery is an iterative…
The rapid evolution of artificial intelligence has led to expectations of transformative impact on science, yet current systems remain fundamentally limited in enabling genuine scientific discovery. This perspective contends that progress…
Since language models (LMs) now outperform average humans on many challenging tasks, it has become increasingly difficult to develop challenging, high-quality, and realistic evaluations. We address this issue by examining LMs' capabilities…
Recent advances in Large Language Models (LLMs) have introduced a new paradigm for software development, where source code is generated from natural language prompts. While this paradigm significantly boosts development productivity,…
Agents based on large language models have shown great potential in accelerating scientific discovery by leveraging their rich background knowledge and reasoning capabilities. In this paper, we introduce BioDiscoveryAgent, an agent that…
Large Language Models (LLMs) have extended their impact beyond Natural Language Processing, substantially fostering the development of interdisciplinary research. Recently, various LLM-based agents have been developed to assist scientific…