在《我的世界》中与LLM驱动的非玩家角色协作完成任务

$How^{2}$: 如何从过程性如何问题中学习

$How^{2}$: How to learn from procedural How-to questions

本文提出$How^{2}$框架，使智能体能提问、存储并复用如何问题答案，提升长期学习能力。在Plancraft环境中，抽象化答案对任务完成更有效。

指代歧义与澄清请求：比较人类与LLM行为

Referential ambiguity and clarification requests: comparing human and LLM behaviour

本研究构建新语料库比较人类与LLM在任务导向对话中面对歧义时的澄清提问行为，发现两者相关性低且表现相反，且推理能力能提升LLM提问的频率与相关性。

LLMs作为多人UNO中的智能体合作玩家

LLMs as Agentic Cooperative Players in Multiplayer UNO

研究让LLM作为合作玩家在UNO中协助他人获胜，发现尽管不同规模模型均超越随机基线，但鲜少能显著帮助队友。

本体忠实的非玩家角色对话生成

Ontologically Faithful Generation of Non-Player Character Dialogues

提出KNUDGE任务，基于《天外世界》游戏数据生成忠实于本体和任务细节的非玩家角色对话树，实验显示神经模型表现胜任但仍有提升空间。

PLAYER*：在谋杀之谜游戏中增强基于大语言模型的多智能体通信与交互

PLAYER*: Enhancing LLM-based Multi-Agent Communication and Interaction in Murder Mystery Games

本研究推出多智能体推理数据集WellPlay并提出PLAYER*框架，通过感知状态表示与信息驱动策略解决谋杀之谜游戏的推理挑战，在推理效果与交互表现上优于现有方法。

大型视觉语言模型是优秀的游戏玩家吗？

Are Large Vision Language Models Good Game Players?

针对现有LVLMs评估基准的不足，提出基于游戏的评估框架\method{}，通过四个核心任务全面评估模型在结构化环境中的认知推理能力，并实验揭示了模型在长结构化输出和密集元素感知上的局限。

Learning to Execute Actions or Ask Clarification Questions

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 an intelligent builder agent in a simulated building environment (Minecraft) that can build whatever users wish to build by just talking to the agent. In order to achieve this goal, such agents need to be able to take the initiative by asking clarification questions when further information is needed. Existing works on Minecraft Corpus Dataset only learn to execute instructions neglecting the importance of asking…

Toward Automated Quest Generation in Text-Adventure Games

Interactive fictions, or text-adventures, are games in which a player interacts with a world entirely through textual descriptions and text actions. Text-adventure games are typically structured as puzzles or quests wherein the player must execute certain actions in a certain order to succeed. In this paper, we consider the problem of procedurally generating a quest, defined as a series of actions required to progress towards a goal, in a text-adventure game. Quest generation in text environments is challenging because they must be semantically coherent. We present and evaluate two quest gener…

通过帮助反馈与智能体交互以改善协作环境中的基础语言理解

Improving Grounded Language Understanding in a Collaborative Environment by Interacting with Agents Through Help Feedback

本研究通过IGLU竞赛中的交互式基础语言理解任务，探索人类提供多种帮助反馈以引导AI智能体，并分析其影响，从而提升AI在协作环境中的表现。

Tie-breaker: Using language models to quantify gender bias in sports journalism

Gender bias is an increasingly important issue in sports journalism. In this work, we propose a language-model-based approach to quantify differences in questions posed to female vs. male athletes, and apply it to tennis post-match interviews. We find that journalists ask male players questions that are generally more focused on the game when compared with the questions they ask their female counterparts. We also provide a fine-grained analysis of the extent to which the salience of this bias depends on various factors, such as question type, game outcome or player rank.