The rise and potential of large language model based agents: A survey

Z Xi, W Chen, X Guo, W He, Y Ding, B Hong… - arXiv preprint arXiv …, 2023 - arxiv.org
For a long time, humanity has pursued artificial intelligence (AI) equivalent to or surpassing
the human level, with AI agents considered a promising vehicle for this pursuit. AI agents are …

Do the rewards justify the means? measuring trade-offs between rewards and ethical behavior in the machiavelli benchmark

A Pan, JS Chan, A Zou, N Li, S Basart… - International …, 2023 - proceedings.mlr.press
Artificial agents have traditionally been trained to maximize reward, which may incentivize
power-seeking and deception, analogous to how next-token prediction in language models …

Learning to model the world with language

J Lin, Y Du, O Watkins, D Hafner, P Abbeel… - arXiv preprint arXiv …, 2023 - arxiv.org
To interact with humans in the world, agents need to understand the diverse types of
language that people use, relate them to the visual world, and act based on them. While …

Large language models can implement policy iteration

E Brooks, L Walls, RL Lewis… - Advances in Neural …, 2023 - proceedings.neurips.cc
In this work, we demonstrate a method for implementing policy iteration using a large
language model. While the application of foundation models to RL has received …

Larp: Language-agent role play for open-world games

M Yan, R Li, H Zhang, H Wang, Z Yang… - arXiv preprint arXiv …, 2023 - arxiv.org
Language agents have shown impressive problem-solving skills within defined settings and
brief timelines. Yet, with the ever-evolving complexities of open-world simulations, there's a …

Perceiving the world: Question-guided reinforcement learning for text-based games

Y Xu, M Fang, L Chen, Y Du, JT Zhou… - arXiv preprint arXiv …, 2022 - arxiv.org
Text-based games provide an interactive way to study natural language processing. While
deep reinforcement learning has shown effectiveness in developing the game playing …

A survey on large language model-based game agents

S Hu, T Huang, F Ilhan, S Tekin, G Liu… - arXiv preprint arXiv …, 2024 - arxiv.org
The development of game agents holds a critical role in advancing towards Artificial General
Intelligence (AGI). The progress of LLMs and their multimodal counterparts (MLLMs) offers …

ScriptWorld: text based environment for learning procedural knowledge

A Joshi, A Ahmad, U Pandey, A Modi - arXiv preprint arXiv:2307.03906, 2023 - arxiv.org
Text-based games provide a framework for developing natural language understanding and
commonsense knowledge about the world in reinforcement learning based agents. Existing …

Self-imitation learning for action generation in text-based games

Z Shi, Y Xu, M Fang, L Chen - … of the 17th Conference of the …, 2023 - aclanthology.org
In this work, we study reinforcement learning (RL) in solving text-based games. We address
the challenge of combinatorial action space, by proposing a confidence-based self-imitation …

In-context policy iteration

E Brooks, LA Walls, R Lewis, S Singh - NeurIPS 2022 Foundation …, 2022 - openreview.net
This work presents In-Context Policy Iteration, an algorithm for performing Reinforcement
Learning (RL), in-context, using foundation models. While the application of foundation …