Related papers: ASTER -- Agentic Science Toolkit for Exoplanet Res…
Contemporary exoplanet and brown dwarf atmospheric research relies heavily on retrieval frameworks to recover thermal and chemical properties and perform model comparison in an observational data-driven approach. However, the computational…
Submillimeter observations are a key for answering many of the big questions in modern-day astrophysics, such as how stars and planets form, how galaxies evolve, and how material cycles through stars and the interstellar medium. With the…
To address the the problem of calibration of instrument systematics in transit light curves, we present the Python package ExoTiC-ISM. Transit spectroscopy can reveal many different chemical components in exoplanet atmospheres, but such…
With over 1800 planets discovered outside of the Solar System in the past two decades, the field of exoplanetology has broadened our perspective on planetary systems. Research priorities are now moving from planet detection to planet…
Large-scale photometric surveys are revolutionizing astronomy by delivering unprecedented amounts of data. The rich data sets from missions such as the NASA Kepler and TESS satellites, and the upcoming ESA PLATO mission, are a treasure…
It is possible to learn a great deal about exoplanet atmospheres even when we cannot spatially resolve the planets from their host stars. In this chapter, we overview the basic techniques used to characterize transiting exoplanets -…
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing and assessing agent behavior. Most current tools are limited,…
This study develops a robust framework for exoplanet characterization by leveraging asteroseismic constraints on host stars. Using precise photometric data from missions such as \textit{Kepler} and \textit{TESS}, we derive stellar…
We have entered the era of the James Webb Space Telescope (JWST). We use the first JWST transmission spectrum of the hot Saturn-mass exoplanet, WASP-39 b, obtained with the NIRSpec instrument in the 3-5 $\mu$m range to investigate (a) what…
Artificial Intelligence (AI) has transformed robotics, healthcare, industry, and scientific discovery, yet a major frontier may lie beyond Earth. Space exploration and settlement offer vast environments and resources, but impose constraints…
This paper details two novel frameworks for developing autonomous, agentic AI in scientific workflows. Both systems leverage a hybrid Local Body, Remote Brain architecture via Google Colab, utilizing Python-based local orchestrators to…
Existing tool-augmented agentic systems are limited in the real world by (i) black-box reasoning steps that undermine trust of decision-making and pose safety risks, (ii) poor multimodal integration, which is inherently critical for…
The techniques of laser cooling combined with atom interferometry make possible the realization of very sensitive and accurate inertial sensors like gyroscopes or accelerometers. Besides earth-based developments, the use of these techniques…
The James Webb Space Telescope (JWST) will perform exoplanet transit spectroscopy in the coming decade promising transformative science results. All four instruments on board can be used for this technique which reconstructs the atmospheric…
The Solar TErrestrial RElations Observatory - \emph{STEREO}, is a system of two identical spacecraft in Heliocentric Earth orbit. We use the two Heliospheric Imagers (HI), which are wide angle imagers with multi-baffle systems to do high…
LLM agents hold significant promise for advancing scientific research. To accelerate this progress, we introduce AIRS-Bench (the AI Research Science Benchmark), a suite of 20 tasks sourced from state-of-the-art machine learning papers.…
The Copilot for Real-world Experimental Scientist (CRESt) system empowers researchers to control autonomous laboratories through conversational AI, providing a seamless interface for managing complex experimental workflows. We have enhanced…
Context-dependent semantic parsing has proven to be an important yet challenging task. To leverage the advances in context-independent semantic parsing, we propose to perform follow-up query analysis, aiming to restate context-dependent…
Environmental monitoring is crucial to our understanding of climate change, biodiversity loss and pollution. The availability of large-scale spatio-temporal data from sources such as sensors and satellites allows us to develop sophisticated…
As Large Language Models (LLMs) become ubiquitous across various scientific domains, their lack of ability to perform complex tasks like running simulations or to make complex decisions limits their utility. LLM-based agents bridge this gap…