Related papers: Agentic Exploration of Physics Models

The adequate testing of stateful software systems is a hard and costly activity. Failures that result from complex stateful interactions can be of high impact, and it can be hard to replicate failures resulting from erroneous stateful…

Language-conditioned robotic skills make it possible to apply the high-level reasoning of Large Language Models (LLMs) to low-level robotic control. A remaining challenge is to acquire a diverse set of fundamental skills. Existing…

Researchers are investing substantial effort in developing powerful general-purpose agents, wherein Foundation Models are used as modules within agentic systems (e.g. Chain-of-Thought, Self-Reflection, Toolformer). However, the history of…

Autonomous artificial agents must be able to learn behaviors in complex environments without humans to design tasks and rewards. Designing these functions for each environment is not feasible, thus, motivating the development of intrinsic…

The research field of Artificial Life studies how life-like phenomena such as autopoiesis, agency, or self-regulation can self-organize in computer simulations. In cellular automata (CA), a key open-question has been whether it it is…

This paper engages in a speculative exploration of the concept of an artificial agent capable of conducting research. Initially, it examines how the act of research can be conceptually characterized, aiming to provide a starting point for…

Von Neuman's work on universal machines and the hardware development have allowed the simulation of dynamical systems through a large set of interacting agents. This is a bottom-up approach which tries to derive global properties of a…

Model free reinforcement learning suffers from the high sampling complexity inherent to robotic manipulation or locomotion tasks. Most successful approaches typically use random sampling strategies which leads to slow policy convergence. In…

Machine learning with application to questions in the physical sciences has become a widely used tool, successfully applied to classification, regression and optimization tasks in many areas. Research focus mostly lies in improving the…

A long-standing challenge in economics lies not in the lack of intuition, but in the difficulty of translating intuitive insights into verifiable research. To address this challenge, we introduce AgentEconomist, an end-to-end interactive…

Agent-based modeling and simulation has evolved as a powerful tool for modeling complex systems, offering insights into emergent behaviors and interactions among diverse agents. Integrating large language models into agent-based modeling…

Machine learning has proven to be a valuable tool to approximate functions in high-dimensional spaces. Unfortunately, analysis of these models to extract the relevant physics is never as easy as applying machine learning to a large dataset…

Physics-driven discovery in an autonomous experiment has emerged as a dream application of machine learning in physical sciences. Here we develop and experimentally implement a deep kernel learning workflow combining the correlative…

Scientists investigate the dynamics of complex systems with quantitative models, employing them to synthesize knowledge, to explain observations, and to forecast future system behavior. Complete specification of systems is impossible, so…

Machine learning is increasingly transforming various scientific fields, enabled by advancements in computational power and access to large data sets from experiments and simulations. As artificial intelligence (AI) continues to grow in…

Discovering explicit physical laws has traditionally depended on human intuition and domain expertise. Recent advances in artificial intelligence, particularly large language models (LLMs), offer a new route to accelerate this process by…

The era of Large Language Models (LLMs) presents a new opportunity for interpretability--agentic interpretability: a multi-turn conversation with an LLM wherein the LLM proactively assists human understanding by developing and leveraging a…

Engineered image-based biomarkers offer a clinically interpretable alternative to black-box AI in computational pathology, yet their discovery remains largely intuition-driven, guided by fragmented literature rather than rigorous biological…

Life and physical sciences have always been quick to adopt the latest advances in machine learning to accelerate scientific discovery. Examples of this are cell segmentation or cancer detection. Nevertheless, these exceptional results are…

Artificial Intelligence (AI), especially AI agents, is increasingly being applied to chemistry, healthcare, and manufacturing to enhance productivity. In this review, we discuss the progress of AI and agentic AI in areas related to, and…