Recent advances in deep learning based dialogue systems: A systematic survey
Dialogue systems are a popular natural language processing (NLP) task as it is promising in
real-life applications. It is also a complicated task since many NLP tasks deserving study are …
real-life applications. It is also a complicated task since many NLP tasks deserving study are …
Webshop: Towards scalable real-world web interaction with grounded language agents
Most existing benchmarks for grounding language in interactive environments either lack
realistic linguistic elements, or prove difficult to scale up due to substantial human …
realistic linguistic elements, or prove difficult to scale up due to substantial human …
Can large language models play text games well? current state-of-the-art and open questions
Large language models (LLMs) such as ChatGPT and GPT-4 have recently demonstrated
their remarkable abilities of communicating with human users. In this technical report, we …
their remarkable abilities of communicating with human users. In this technical report, we …
Tvshowguess: Character comprehension in stories as speaker guessing
We propose a new task for assessing machines' skills of understanding fictional characters
in narrative stories. The task, TVShowGuess, builds on the scripts of TV series and takes the …
in narrative stories. The task, TVShowGuess, builds on the scripts of TV series and takes the …
Arigraph: Learning knowledge graph world models with episodic memory for llm agents
Advancements in generative AI have broadened the potential applications of Large
Language Models (LLMs) in the development of autonomous agents. Achieving true …
Language Models (LLMs) in the development of autonomous agents. Achieving true …
Conceptual reinforcement learning for language-conditioned tasks
Despite the broad application of deep reinforcement learning (RL), transferring and adapting
the policy to unseen but similar environments is still a significant challenge. Recently, the …
the policy to unseen but similar environments is still a significant challenge. Recently, the …
Pre-trained language models as prior knowledge for playing text-based games
Recently, text world games have been proposed to enable artificial agents to understand
and reason about real-world scenarios. These text-based games are challenging for artificial …
and reason about real-world scenarios. These text-based games are challenging for artificial …
Perceiving the world: Question-guided reinforcement learning for text-based games
Text-based games provide an interactive way to study natural language processing. While
deep reinforcement learning has shown effectiveness in developing the game playing …
deep reinforcement learning has shown effectiveness in developing the game playing …
A survey on large language model-based game agents
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 …
Intelligence (AGI). The progress of LLMs and their multimodal counterparts (MLLMs) offers …
A systematic survey of text worlds as embodied natural language environments
PA Jansen - arXiv preprint arXiv:2107.04132, 2021 - arxiv.org
Text Worlds are virtual environments for embodied agents that, unlike 2D or 3D
environments, are rendered exclusively using textual descriptions. These environments offer …
environments, are rendered exclusively using textual descriptions. These environments offer …