Closed-source agents suffer from several issues such as a lack of affordability, transparency,
and reproducibility, particularly on complex interactive tasks. This motivates the …

We introduce Lumos, a novel framework for training language agents that employs a unified
data format and a modular architecture based on open-source large language models …

We explore the creative problem-solving capabilities of modern large language models
(LLMs) in a constrained setting. The setting requires circumventing a cognitive bias known in …

Structured Complex Task Decomposition (SCTD) is the problem of breaking down a
complex real-world task (such as planning a wedding) into a directed acyclic graph over …

While text style transfer has many applications across natural language processing, the core
premise of transferring from a single source style is unrealistic in a real-world setting. In this …

In this paper we explore the capability of an agent to construct a logical sequence of action
steps thereby assembling a strategic procedural plan. This plan is crucial for navigating from …

Many algorithms for aligning LLMs with human preferences assume that human preferences
are binary and deterministic. However, human preferences can vary across individuals, and …

Understanding the abilities of LLMs to reason about natural language plans, such as
instructional text and recipes, is critical to reliably using them in decision-making systems. A …

Language models are exhibiting increasing capability in knowledge utilization and
reasoning. However, when applied as agents in embodied environments, they often suffer …

Recently, large pre-trained language models (LLMs) have demonstrated superior language
understanding abilities, including zero-shot causal reasoning. However, it is unclear to what …