Related papers: Bridging the Prototype-Production Gap: A Multi-Age…
Planning has become a central capability for contemporary agent systems in navigating complex, long-horizon tasks, yet existing approaches predominantly rely on fixed, hand-crafted planning structures that lack the flexibility to adapt to…
Although significant progress has been made in many tasks within the field of Natural Language Processing (NLP), Controlled Text Generation (CTG) continues to face numerous challenges, particularly in achieving fine-grained conditional…
Behavioral analysis of tutoring dialogues is essential for understanding student learning, yet manual coding remains a bottleneck. We present a methodology where LLM coding agents autonomously improve the prompts used by LLM classifiers to…
The Notebook validation tool nbval allows to load and execute Python code from a Jupyter notebook file. While computing outputs from the cells in the notebook, these outputs are compared with the outputs saved in the notebook file, treating…
Deep research has revolutionized data analysis, yet data scientists still devote substantial time to manually crafting visualizations, highlighting the need for robust automation from natural language queries. However, current systems…
This paper proposes the use of notebooks for the design documentation and tool interaction in the rigorous design of embedded systems. Conventionally, a notebook is a sequence of cells alternating between (textual) code and prose to form a…
Many software projects implement APIs and algorithms in multiple programming languages. Maintaining such projects is tiresome, as developers have to ensure that any change (e.g., a bug fix or a new feature) is being propagated, timely and…
Spreadsheet programming is challenging. Programmers use spreadsheet programming knowledge (e.g., formulas) and problem-solving skills to combine actions into complex tasks. Advancements in large language models have introduced language…
In an era of widespread influence of Natural Language Processing (NLP), there have been multiple research efforts to supplant traditional manual coding techniques with automated systems capable of generating solutions autonomously. With…
Human cognitive development is shaped not only by individual effort but by structured social interaction, where role-based exchanges such as those between a tutor and a learner, enable solutions that neither could achieve alone. Inspired by…
Software developers often repeat code changes, known as "code change patterns" (CPATs), within and across projects. Automating these CPATs accelerates development, but current Transformation by Example (TBE) techniques are limited by the…
Code agents are advancing rapidly, but debugging them is becoming increasingly difficult. As frameworks orchestrate parallel tool calls and multi-stage workflows over complex tasks, making the agent's state transitions and error propagation…
We report a case study where an existing materials science course was modified to include numerical simulation projects on the micromagnetic behavior of materials. The Ubermag micromagnetic simulation software package is used in order to…
Large language models (LLMs) have advanced code generation from single-function tasks to competitive-programming problems, but existing multi-agent solutions either rely on costly large-scale (>30B) models or collapse when downsized to…
Agentic systems have recently emerged as a promising tool to automate literature-based ideation. However, current systems often remain black-box, with limited transparency or control for researchers. Our work introduces TrustResearcher, a…
The automation of scientific discovery represents a critical milestone in Artificial Intelligence (AI) research. However, existing agentic systems for science suffer from two fundamental limitations: rigid, pre-programmed workflows that…
Scientific data visualization is pivotal for transforming raw data into comprehensible visual representations, enabling pattern recognition, forecasting, and the presentation of data-driven insights. However, novice users often face…
Skele-Code is a natural-language and graph-based interface for building workflows with AI agents, designed especially for less or non-technical users. It supports incremental, interactive notebook-style development, and each step is…
Most repository-level code translation and validation techniques have been evaluated on a single source-target programming language (PL) pair, owing to the complex engineering effort required to adapt new PL pairs. Programming agents can…
Context: LLM-based multi-agent systems enable automation and decision support in software development, yet existing studies rely on benchmark datasets offering only binary pass-or-fail results, limiting insight into real-world…