Related papers: Simple Agents Outperform Experts in Biomedical Ima…
Recent advances in agentic AI are shifting automation from discrete tools to proactive multi-agent systems that coordinate multi-specialized capabilities behind unified interfaces. However, today's agent systems typically rely on hard-coded…
Scientific workflows in computational chemistry and materials science typically involve multiple interdependent steps, such as model preparation, system construction, simulation execution, and data analysis, that researchers have refined…
Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually convert research questions into workflow specifications, a…
While large language models have significantly accelerated scientific code generation, comprehensively evaluating the generated code remains a major challenge. Traditional benchmarks reduce evaluation to test-case matching, an approach…
AI agents hold the potential to revolutionize scientific productivity by automating literature reviews, replicating experiments, analyzing data, and even proposing new directions of inquiry; indeed, there are now many such agents, ranging…
Agentic AI marks a major shift in how autonomous systems reason, plan, and execute multi-step tasks. Unlike traditional single model prompting, agentic workflows integrate multiple specialized agents with different Large Language…
Using multiple agents was found to improve the debugging capabilities of Large Language Models. However, increasing the number of LLM-agents has several drawbacks such as increasing the running costs and rising the risk for the agents to…
Software development is a complex, multi-phase process traditionally requiring collaboration among individuals with diverse expertise. We propose AgentMesh, a Python-based framework that uses multiple cooperating LLM-powered agents to…
As the focus in LLM-based coding shifts from static single-step code generation to multi-step agentic interaction with tools and environments, understanding which tasks will challenge agents and why becomes increasingly difficult. This is…
The remarkable capabilities of Large Language Model (LLM)-driven agents have enabled sophisticated systems to tackle complex, multi-step tasks, but their escalating costs threaten scalability and accessibility. This work presents the first…
Recent advancements in visual generative models have enabled high-quality image and video generation, opening diverse applications. However, evaluating these models often demands sampling hundreds or thousands of images or videos, making…
Tool use has turned large language models (LLMs) into powerful agents that can perform complex multi-step tasks by dynamically utilising external software components. However, these tools must be implemented in advance by human developers,…
Critical domain knowledge typically resides with few experts, creating organizational bottlenecks in scalability and decision-making. Non-experts struggle to create effective visualizations, leading to suboptimal insights and diverting…
Recent advances in code generation models have unlocked unprecedented opportunities for automating feature engineering, yet their adoption in real-world ML teams remains constrained by critical challenges: (i) the scarcity of datasets…
Historically, scientific discovery has been a lengthy and costly process, demanding substantial time and resources from initial conception to final results. To accelerate scientific discovery, reduce research costs, and improve research…
Large Language Models (LLMs) have emerged as powerful tools for accelerating scientific discovery, yet their static knowledge and hallucination issues hinder autonomous research applications. Recent advances integrate LLMs into agentic…
This position paper argues that optimization problem solving can transition from expert-dependent to evolutionary agentic workflows. Traditional optimization practices rely on human specialists for problem formulation, algorithm selection,…
Data science plays a critical role in transforming complex data into actionable insights across numerous domains. Recent developments in large language models (LLMs) have significantly automated data science workflows, but a fundamental…
We focus on the problem of designing an artificial agent (AI), capable of assisting a human user to complete a task. Our goal is to guide human users towards optimal task performance while keeping their cognitive load as low as possible.…
This paper introduces BioAgent Bench, a benchmark dataset and an evaluation suite designed for measuring the performance and robustness of AI agents in common bioinformatics tasks. The benchmark contains curated end-to-end tasks (e.g.,…