Related papers: Automating Care by Self-maintainability for Full L…

Guiding large language models with a selected set of human-authored demonstrations is a common practice for improving LLM applications. However, human effort can be costly, especially in specialized domains (e.g., clinical diagnosis), and…

The rapid growth of biomedical data, tools, and literature has created a fragmented research landscape that outpaces human expertise. While AI agents offer a solution, they typically rely on static, manually curated toolsets, limiting their…

The cognitive sciences aim to understand intelligence by formalizing underlying operations as computational models. Traditionally, this follows a cycle of discovery where researchers develop paradigms, collect data, and test predefined…

The paper surveys automated scientific discovery, from equation discovery and symbolic regression to autonomous discovery systems and agents. It discusses the individual approaches from a "big picture" perspective and in context, but also…

This paper explores the potential of a multidisciplinary approach to testing and aligning artificial intelligence (AI), specifically focusing on large language models (LLMs). Due to the rapid development and wide application of LLMs,…

The population of the elderly people has kept increasing rapidly over the world in the past decades. Solutions that are able to effectively support the elderly people to live independently at their home are thus urgently needed. Ambient…

This paper presents a proof-of-concept study that examines the utilization of generative AI and mobile robotics for autonomous laboratory monitoring in the pharmaceutical R&D laboratory. The study investigates the potential advantages of…

Segment anything model (SAM) has emerged as the leading approach for zero-shot learning in segmentation tasks, offering the advantage of avoiding pixel-wise annotations. It is particularly appealing in medical image segmentation, where the…

Scientific discovery increasingly entails long-horizon exploration of complex hypothesis spaces, yet most existing approaches emphasize final performance while offering limited insight into how scientific exploration unfolds over time,…

The Automated Model Evaluation (AutoEval) framework entertains the possibility of evaluating a trained machine learning model without resorting to a labeled testing set. Despite the promise and some decent results, the existing AutoEval…

Scientific research is being reshaped by AI systems that move beyond isolated assistance toward longer-horizon workflows spanning literature grounding, hypothesis generation, experimentation, validation, reporting, and revision. This shift…

Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance remains limited by underlying tool constraints. To this end, we propose tool amplification, a…

Modern biology frequently relies on machine learning to provide predictions and improve decision processes. There have been recent calls for more scrutiny on machine learning performance and possible limitations. Here we present a set of…

AI agents hold growing promise for accelerating scientific discovery; yet, a lack of frontier evaluations hinders adoption into real workflows. Expert-written benchmarks have proven effective at measuring AI reasoning, but most at this…

The rapid advancement of large language models (LLMs) is fundamentally reshaping software engineering (SE), driving a paradigm shift in both academic research and industrial practice. While top-tier SE venues continue to show sustained or…

Testing of autonomous systems is extremely important as many of them are both safety-critical and security-critical. The architecture and mechanism of such systems are fundamentally different from traditional control software, which appears…

Given the complexity of real-world, unstructured domains, it is often impossible or impractical to design models that include every feature needed to handle all possible scenarios that an autonomous system may encounter. For an autonomous…

In artificial intelligence (AI), the complexity of many models and processes surpasses human understanding, making it challenging to determine why a specific prediction is made. This lack of transparency is particularly problematic in…

Continual learning refers to the ability of a biological or artificial system to seamlessly learn from continuous streams of information while preventing catastrophic forgetting, i.e., a condition in which new incoming information strongly…

The Simulation Environment for Atomistic and Molecular Modeling (SEAMM) is an open-source software package written in Python that provides a graphical interface for setting up, executing, and analyzing molecular and materials simulations.…