Related papers: DVM: Towards Controllable LLM Agents in Social Deduction Games

DVM: Towards Controllable LLM Agents in Social Deduction Games

URL: http://arxiv.org/abs/2501.06695v1
Date: Sun, 12 Jan 2025 03:11:20 GMT
Title: DVM: Towards Controllable LLM Agents in Social Deduction Games
Authors: Zheng Zhang, Yihuai Lan, Yangsen Chen, Lei Wang, Xiang Wang, Hao Wang,
Abstract summary: Large Language Models (LLMs) have advanced the capability of game agents in social deduction games (SDGs)<n>We present DVM, a novel framework for developing controllable LLM agents for SDGs.<n>We demonstrate DVM's implementation on one of the most popular SDGs, Werewolf.
Score: 16.826397707182963
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Abstract: Large Language Models (LLMs) have advanced the capability of game agents in social deduction games (SDGs). These games rely heavily on conversation-driven interactions and require agents to infer, make decisions, and express based on such information. While this progress leads to more sophisticated and strategic non-player characters (NPCs) in SDGs, there exists a need to control the proficiency of these agents. This control not only ensures that NPCs can adapt to varying difficulty levels during gameplay, but also provides insights into the safety and fairness of LLM agents. In this paper, we present DVM, a novel framework for developing controllable LLM agents for SDGs, and demonstrate its implementation on one of the most popular SDGs, Werewolf. DVM comprises three main components: Predictor, Decider, and Discussor. By integrating reinforcement learning with a win rate-constrained decision chain reward mechanism, we enable agents to dynamically adjust their gameplay proficiency to achieve specified win rates. Experiments show that DVM not only outperforms existing methods in the Werewolf game, but also successfully modulates its performance levels to meet predefined win rate targets. These results pave the way for LLM agents' adaptive and balanced gameplay in SDGs, opening new avenues for research in controllable game agents.

Related papers

Do LLMs trust AI regulation? Emerging behaviour of game-theoretic LLM agents [61.132523071109354]
This paper investigates the interplay between AI developers, regulators and users, modelling their strategic choices under different regulatory scenarios. Our research identifies emerging behaviours of strategic AI agents, which tend to adopt more "pessimistic" stances than pure game-theoretic agents.
arXiv Detail & Related papers (2025-04-11T15:41:21Z)
Cultivating Game Sense for Yourself: Making VLMs Gaming Experts [23.370716496046217]
We propose a paradigm shift in gameplay agent design. Instead of directly controlling gameplay, VLM develops specialized execution modules tailored for tasks like shooting and combat. These modules handle real-time game interactions, elevating VLM to a high-level developer.
arXiv Detail & Related papers (2025-03-27T08:40:47Z)
AVA: Attentive VLM Agent for Mastering StarCraft II [56.07921367623274]
We introduce Attentive VLM Agent (AVA), a multimodal StarCraft II agent that aligns artificial agent perception with the human gameplay experience. Our agent addresses this limitation by incorporating RGB visual inputs and natural language observations that more closely simulate human cognitive processes during gameplay.
arXiv Detail & Related papers (2025-03-07T12:54:25Z)
LLMs May Not Be Human-Level Players, But They Can Be Testers: Measuring Game Difficulty with LLM Agents [10.632179121247466]
We propose a general game-testing framework using LLM agents and test it on two widely played strategy games: Wordle and Slay the Spire. Our results reveal an interesting finding: although LLMs may not perform as well as the average human player, their performance, when guided by simple, generic prompting techniques, shows a statistically significant and strong correlation with difficulty indicated by human players. This suggests that LLMs could serve as effective agents for measuring game difficulty during the development process.
arXiv Detail & Related papers (2024-10-01T18:40:43Z)
Evaluating and Enhancing LLMs Agent based on Theory of Mind in Guandan: A Multi-Player Cooperative Game under Imperfect Information [36.11862095329315]
Large language models (LLMs) have shown success in handling simple games with imperfect information. This study investigates the applicability of knowledge acquired by open-source and API-based LLMs to sophisticated text-based games.
arXiv Detail & Related papers (2024-08-05T15:36:46Z)
Toward Optimal LLM Alignments Using Two-Player Games [86.39338084862324]
In this paper, we investigate alignment through the lens of two-agent games, involving iterative interactions between an adversarial and a defensive agent. We theoretically demonstrate that this iterative reinforcement learning optimization converges to a Nash Equilibrium for the game induced by the agents. Experimental results in safety scenarios demonstrate that learning in such a competitive environment not only fully trains agents but also leads to policies with enhanced generalization capabilities for both adversarial and defensive agents.
arXiv Detail & Related papers (2024-06-16T15:24:50Z)
Minimax Exploiter: A Data Efficient Approach for Competitive Self-Play [12.754819077905061]
Minimax Exploiter is a game theoretic approach to exploiting Main Agents that leverages knowledge of its opponents. We validate our approach in a diversity of settings, including simple turn based games, the arcade learning environment, and For Honor, a modern video game.
arXiv Detail & Related papers (2023-11-28T19:34:40Z)
ALYMPICS: LLM Agents Meet Game Theory -- Exploring Strategic Decision-Making with AI Agents [77.34720446306419]
Alympics is a systematic simulation framework utilizing Large Language Model (LLM) agents for game theory research. Alympics creates a versatile platform for studying complex game theory problems.
arXiv Detail & Related papers (2023-11-06T16:03:46Z)
Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game [40.438765131992525]
We develop strategic language agents that generate flexible language actions and possess strong decision-making abilities. To mitigate the intrinsic bias in language actions, our agents use an LLM to perform deductive reasoning and generate a diverse set of action candidates. Experiments show that our agents overcome the intrinsic bias and outperform existing LLM-based agents in the Werewolf game.
arXiv Detail & Related papers (2023-10-29T09:02:57Z)
LLM-Based Agent Society Investigation: Collaboration and Confrontation in Avalon Gameplay [55.12945794835791]
Using Avalon as a testbed, we employ system prompts to guide LLM agents in gameplay. We propose a novel framework, tailored for Avalon, features a multi-agent system facilitating efficient communication and interaction. Results affirm the framework's effectiveness in creating adaptive agents and suggest LLM-based agents' potential in navigating dynamic social interactions.
arXiv Detail & Related papers (2023-10-23T14:35:26Z)
AgentBench: Evaluating LLMs as Agents [88.45506148281379]
Large Language Models (LLMs) are becoming increasingly smart and autonomous, targeting real-world pragmatic missions beyond traditional NLP tasks. We present AgentBench, a benchmark that currently consists of 8 distinct environments to assess LLM-as-Agent's reasoning and decision-making abilities.
arXiv Detail & Related papers (2023-08-07T16:08:11Z)
Deep Policy Networks for NPC Behaviors that Adapt to Changing Design Parameters in Roguelike Games [137.86426963572214]
Turn-based strategy games like Roguelikes, for example, present unique challenges to Deep Reinforcement Learning (DRL) We propose two network architectures to better handle complex categorical state spaces and to mitigate the need for retraining forced by design decisions.
arXiv Detail & Related papers (2020-12-07T08:47:25Z)

This list is automatically generated from the titles and abstracts of the papers in this site.