With generative AI advances, the exciting potential for autonomous agents to manage daily
tasks via natural language commands has emerged. However, cur rent agents are primarily …

The advent of large language models trained on code (code LLMs) has led to significant
progress in language-to-code generation. State-of-the-art approaches in this area combine …

We address the general task of structured commonsense reasoning: given a natural
language input, the goal is to generate a graph such as an event--or a reasoning-graph. To …

Recently, large language models (LLMs), especially those that are pretrained on code, have
demonstrated strong capabilities in generating programs from natural language inputs …

LLMs can now act as autonomous agents that interact with digital environments and
complete specific objectives (eg, arranging an online meeting). However, accuracy is still far …

Performing tasks on the web presents fundamental challenges to large language models
(LLMs), including combinatorially large open-world tasks and variations across web …

Robotic agents performing domestic chores by natural language directives are required to
master the complex job of navigating environment and interacting with objects in the …

Large language models (LLMs) have demonstrated remarkable capabilities in performing a
range of instruction following tasks in few and zero-shot settings. However, teaching LLMs to …

Abstract Reasoning about actions and change (RAC) is essential to understand and interact
with the ever-changing environment. Previous AI research has shown the importance of …

This paper investigates human instruction following for robotic manipulation via a hybrid,
modular system with symbolic and connectionist elements. Symbolic methods build modular …