Cognitive architectures for language agents

TR Sumers, S Yao, K Narasimhan… - arXiv preprint arXiv …, 2023 - arxiv.org
Recent efforts have incorporated large language models (LLMs) with external resources (eg,
the Internet) or internal control flows (eg, prompt chaining) for tasks requiring grounding or …

Teach: Task-driven embodied agents that chat

A Padmakumar, J Thomason, A Shrivastava… - Proceedings of the …, 2022 - ojs.aaai.org
Robots operating in human spaces must be able to engage in natural language interaction,
both understanding and executing instructions, and using conversation to resolve ambiguity …

Vision-and-language navigation: A survey of tasks, methods, and future directions

J Gu, E Stefani, Q Wu, J Thomason… - arXiv preprint arXiv …, 2022 - arxiv.org
A long-term goal of AI research is to build intelligent agents that can communicate with
humans in natural language, perceive the environment, and perform real-world tasks. Vision …

Building cooperative embodied agents modularly with large language models

H Zhang, W Du, J Shan, Q Zhou, Y Du… - arXiv preprint arXiv …, 2023 - arxiv.org
Large Language Models (LLMs) have demonstrated impressive planning abilities in single-
agent embodied tasks across various domains. However, their capacity for planning and …

Visually Grounded Language Learning: a review of language games, datasets, tasks, and models

A Suglia, I Konstas, O Lemon - Journal of Artificial Intelligence Research, 2024 - jair.org
In recent years, several machine learning models have been proposed. They are trained
with a language modelling objective on large-scale text-only data. With such pretraining …

Conversational ai for multi-agent communication in natural language: Research directions at the interaction lab

O Lemon - Ai Communications, 2022 - journals.sagepub.com
Research at the Interaction Lab focuses on human-agent communication using
conversational Natural Language. The ultimate goal is to create systems where humans and …

Learning to execute actions or ask clarification questions

Z Shi, Y Feng, A Lipani - arXiv preprint arXiv:2204.08373, 2022 - arxiv.org
Collaborative tasks are ubiquitous activities where a form of communication is required in
order to reach a joint goal. Collaborative building is one of such tasks. We wish to develop …

MindCraft: Theory of mind modeling for situated dialogue in collaborative tasks

CP Bara, S CH-Wang, J Chai - arXiv preprint arXiv:2109.06275, 2021 - arxiv.org
An ideal integration of autonomous agents in a human world implies that they are able to
collaborate on human terms. In particular, theory of mind plays an important role in …

Communicating natural programs to humans and machines

S Acquaviva, Y Pu, M Kryven… - Advances in …, 2022 - proceedings.neurips.cc
Abstract The Abstraction and Reasoning Corpus (ARC) is a set of procedural tasks that tests
an agent's ability to flexibly solve novel problems. While most ARC tasks are easy for …

I cast detect thoughts: Learning to converse and guide with intents and theory-of-mind in dungeons and dragons

P Zhou, A Zhu, J Hu, J Pujara, X Ren… - arXiv preprint arXiv …, 2022 - arxiv.org
We propose a novel task, G4C, to study teacher-student natural language interactions in a
goal-driven and grounded environment. Dungeons and Dragons (D&D), a role-playing …