Related papers: Bricklayer: An Authentic Introduction to the Funct…
Context: Software development tools should work and behave consistently across different programming languages, so that developers do not have to familiarize themselves with new tooling for new languages. Also, being able to combine…
Large language models (LLMs) have unlocked new capabilities of task planning from human instructions. However, prior attempts to apply LLMs to real-world robotic tasks are limited by the lack of grounding in the surrounding scene. In this…
Successful application of large language models (LLMs) to robotic planning and execution may pave the way to automate numerous real-world tasks. Promising recent research has been conducted showing that the knowledge contained in LLMs can…
With easier access to powerful compute resources, there is a growing trend in the field of AI for software development to develop larger and larger language models (LLMs) to address a variety of programming tasks. Even LLMs applied to tasks…
We are witnessing a bloom of AI-powered software driven by Large Language Models (LLMs). Although the applications of these LLMs are impressive and seemingly countless, their unreliability hinders adoption. In fact, the tendency of LLMs to…
Autonomous artificial intelligence (AI) agents have emerged as promising protocols for automatically understanding the language-based environment, particularly with the exponential development of large language models (LLMs). However, a…
Game Design Pillars are natural language artifacts commonly used in game development to communicate a project's core vision and ensure a coherent player experience. Their linguistic nature aligns well with the strengths of Large Language…
Programmatic weak supervision methodologies facilitate the expedited labeling of extensive datasets through the use of label functions (LFs) that encapsulate heuristic data sources. Nonetheless, the creation of precise LFs necessitates…
Large language model (LLM) agents increasingly rely on reusable skills: capability packages that combine instructions, control flow, constraints, and tool calls. In current agent systems, however, skills are still represented by text-heavy…
Grassroots platforms are distributed systems with multiple instances that can (1) operate independently of each other and of any global resource other than the network, and (2) coalesce into ever larger instances, possibly resulting in a…
Whenever a bug occurs in a program, software developers assume that the code is flawed, not the compiler. In fact, if compilers should be correct, they are just normal software with their own bugs. Hard to find, errors in them have…
Numerical software in computational science and engineering often relies on highly-optimized building blocks from libraries such as BLAS and LAPACK, and while such libraries provide portable performance for a wide range of computing…
Creating assembly products demands significant manual effort and expert knowledge in 1) designing the assembly and 2) constructing the product. This paper introduces Prompt-to-Product, an automated pipeline that generates real-world…
This paper introduces the new robot programming language LightRocks (Light Weight Robot Coding for Skills), a domain specific language (DSL) for robot programming. The language offers three different level of abstraction for robot…
We present a comparative study of building with LEGO in three environments: the physical world, a Virtual Reality (VR) counterpart, and a VR setting enhanced with "superpowers". The study aims to understand how traditional creative hands-on…
Large language models (LLMs) are increasingly used to automate feature engineering in tabular learning. Given task-specific information, LLMs can propose diverse feature transformation operations to enhance downstream model performance.…
We introduce a novel dataset designed to benchmark the physical and spatial reasoning capabilities of Large Language Models (LLM) based on topology optimization, a method for computing optimal material distributions within a design space…
Block-based programming environments such as Scratch are increasingly popular in programming education, in particular for young learners. While the use of blocks helps prevent syntax errors, semantic bugs remain common and difficult to…
We present Babel-17, the first programming language for purely functional structured programming (PFSP). Earlier work illustrated PFSP in the framework of a toy research language. Babel-17 takes this earlier work to a new level by showing…
Recent work shows overwhelming evidence that LLMs, even those trained to scale their reasoning trace, perform unsatisfactorily when solving planning problems too complex. Whether the same conclusion holds for LLM formalizers that generate…