Related papers: Autonomous Agents Coordinating Distributed Discove…
Data-driven scientific discovery requires the iterative integration of scientific domain knowledge, statistical expertise, and an understanding of data semantics to make nuanced analytical decisions, e.g., about which variables,…
Autonomous agents powered by large language models (LLMs) have the potential to enhance human capabilities, assisting with digital tasks from sending emails to performing data analysis. The abilities of existing LLMs at such tasks are often…
As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and real environment interaction. Existing agenticinfrastructure remain fragmented…
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…
Recent advancements in Large Language Models (LLMs) have led to a rapid growth of agentic systems capable of handling a wide range of complex tasks. However, current research largely relies on manual, task-specific design, limiting their…
When automated decision systems fail, organizations frequently discover that formally compliant governance infrastructure cannot reconstruct what happened or why. This paper synthesizes an operational governance evidence framework --…
The convergence of large language models and agents is catalyzing a new era of scientific discovery: Agentic Science. While the scientific method is inherently iterative, existing agent frameworks are predominantly static, narrowly scoped,…
Modern scientific research relies on large-scale data, complex workflows, and specialized tools, which existing LLMs and tool-based agents struggle to handle due to limitations in long-horizon planning, robust goal maintenance, and…
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,…
Open-ended self-improving agents can autonomously modify their own structural designs to advance their capabilities and overcome the limits of pre-defined architectures, thus reducing reliance on human intervention. We introduce…
Recent advances in large language models (LLMs) have shown great potential to accelerate drug discovery. However, the specialized nature of biochemical data often necessitates costly domain-specific fine-tuning, posing major challenges.…
We introduce Evolutionary Ensemble (EvE), a decentralized framework that organizes existing, highly capable coding agents into a live, co-evolving system for algorithmic discovery. Rather than reinventing the wheel within the "LLMs as…
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…
This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance mechanisms, and early deployment experience. The performance of agent systems built on LLMs…
Building on the Agentic ROI framework proposed by Liu et al. (2026), this paper introduces knowledge compounding as a new measurable concept in the empirical economics of LLM agents and validates it through a controlled four-query…
Deep research requires reasoning over web evidence to answer open-ended questions, and it is a core capability for AI agents. Yet many deep research agents still rely on implicit, unstructured search behavior that causes redundant…
The rapid proliferation of Claude agent skills has raised the central question of how to effectively leverage, manage, and scale the agent skill ecosystem. In this paper, we propose AgentSkillOS, the first principled framework for skill…
Current AI-assisted innovation systems typically apply a single ideation methodology (such as TRIZ or Design Thinking) using sequential prompt-based workflows that do not preserve intermediate reasoning structure. As a result, insights…
Data science tasks involving tabular data present complex challenges that require sophisticated problem-solving approaches. We propose AutoKaggle, a powerful and user-centric framework that assists data scientists in completing daily data…
Retrieval-Augmented Generation (RAG) enables large language models (LLMs) to access external knowledge sources, but the effectiveness of RAG relies on the coordination between the retriever and the generator. Since these components are…