Related papers: ASTER -- Agentic Science Toolkit for Exoplanet Res…
The process of scientific discovery relies on an interplay of observations, analysis, and hypothesis generation. Machine learning is increasingly being adopted to address individual aspects of this process. However, it remains an open…
Agentic systems built on large language models (LLMs) offer promising capabilities for automating complex workflows in healthcare AI. We introduce mAIstro, an open-source, autonomous multi-agentic framework for end-to-end development and…
Producing optimized and accurate transmission spectra of exoplanets from telescope data has traditionally been a manual and labor-intensive procedure. Here we present the results of the first attempt to improve and standardize this…
Recent improvements in large language models (LLMs) have had a dramatic effect on capabilities and productivity across many disciplines involving critical thinking and writing. The development of the model context protocol (MCP) provides a…
Why bother with asteroseismology while studying exoplanets? There are several answers to this question. Asteroseismology and exoplanetary sciences have much in common and the synergy between the two opens up new aspects in both fields.…
In view of increased interest in object-oriented systems for describing coordinate information, we present a description of the data model used by the Starlink AST library. AST provides a comprehensive range of facilities for attaching…
Agentic data science (ADS) systems are rapidly improving their capability to autonomously analyze, fit, and interpret data, potentially moving towards a future where agents conduct the vast majority of data-science work. However, current…
The chromatic contamination that arises from photospheric heterogeneities e.g. spots and faculae on the host star presents a significant noise source for exoplanet transmission spectra. If this contamination is not corrected for, it can…
Having a need to perform differential photometry for tens of thousands stars in a several square degrees field, we developed Astrokit program. The software corrects the star brightness variations caused by variations of atmospheric…
The fields of astronomy and astrophysics are currently engaged in an unprecedented era of discovery as recent missions have revealed thousands of exoplanets orbiting other stars. While the Kepler Space Telescope mission has enabled most of…
A promising method for detecting earth-sized exoplanets is the timing analysis of a known transit. The technique allows a search for variations in either the transit duration or the center induced by the perturbation of a third body, e.g. a…
Earth Observation (EO) is moving beyond static prediction toward multi-step analytical workflows that require coordinated reasoning over data, tools, and geospatial state. While foundation models and vision-language models have advanced…
We are at a unique timeline in the history of human evolution where we may be able to discover earth-like planets around stars outside our solar system where conditions can support life or even find evidence of life on those planets. With…
Aims. To create a retrieval framework which encapsulates the 3D nature of exoplanet atmospheres, and to apply it to observed emission phase curve and transmission spectra of hot Jupiter exoplanet WASP-43b. Methods. We present our 3D…
Multi-wavelength transit and secondary-eclipse light-curve observations are some of the most powerful techniques to probe the thermo-chemical properties of exoplanets. Although the large planet-to-star brightness contrast and few available…
We present STAgent, an agentic large language model tailored for spatio-temporal understanding, designed to solve complex tasks such as constrained point-of-interest discovery and itinerary planning. STAgent is a specialized model capable…
Earth observation (EO) is essential for understanding the evolving states of the Earth system. Although recent MLLMs have advanced EO research, they still lack the capability to tackle complex tasks that require multi-step reasoning and the…
Rocky planets with temperate conditions provide the best chance for discovering habitable worlds and life outside the Solar System. In the last decades, new instrumental facilities and large observational campaigns have been driven by the…
It is well known that asteroseismology is the unique technique permitting the study of the internal structure of pulsating stars using their pulsational frequencies, which is per se very important. It acquires an additional value when the…
Task-specialized models form the backbone of agentic healthcare systems, enabling the agents to answer clinical queries across tasks such as disease diagnosis, localization, and report generation. Yet, for a given task, a single "best"…