Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games

• URL: http://arxiv.org/abs/2604.11741v1
• Date: Mon, 13 Apr 2026 17:16:23 GMT
• Title: Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games
• Abstract summary: Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings.<n>In this paper, we study a representative multiplayer task, Murder Mystery Games, which require inferring hidden truths based on partial clues provided by roles with different intentions.<n>We propose a collaborative multi-agent framework for evaluating and synthesizing high-quality, role-driven multiplayer game scripts.
• Score: 57.64247186502836
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfect and deceptive information. In this paper, we study a representative multiplayer task, Murder Mystery Games, which require inferring hidden truths based on partial clues provided by roles with different intentions. To address this challenge, we propose a collaborative multi-agent framework for evaluating and synthesizing high-quality, role-driven multiplayer game scripts, enabling fine-grained interaction patterns tailored to character identities (i.e., murderer vs. innocent). Our system generates rich multimodal contexts, including character backstories, visual and textual clues, and multi-hop reasoning chains, through coordinated agent interactions. We design a two-stage agent-monitored training strategy to enhance the reasoning ability of VLMs: (1) chain-of-thought based fine-tuning on curated and synthetic datasets that model uncertainty and deception; (2) GRPO-based reinforcement learning with agent-monitored reward shaping, encouraging the model to develop character-specific reasoning behaviors and effective multimodal multi-hop inference. Extensive experiments demonstrate that our method significantly boosts the performance of VLMs in narrative reasoning, hidden fact extraction, and deception-resilient understanding. Our contributions offer a scalable solution for training and evaluating VLMs under uncertain, adversarial, and socially complex conditions, laying the groundwork for future benchmarks in multimodal multi-hop reasoning under imperfect information.

Related papers

• MMhops-R1: Multimodal Multi-hop Reasoning [89.68086555694084]
  We introduce MMhops, a novel benchmark designed to evaluate and foster multi-modal multi-hop reasoning.<n> MMhops dataset comprises two challenging task formats, Bridging and Comparison.<n>We propose MMhops-R1, a novel multi-modal Retrieval-Augmented Generation framework for dynamic reasoning.
  arXiv  Detail & Related papers  (2025-12-15T17:29:02Z)
• MADIAVE: Multi-Agent Debate for Implicit Attribute Value Extraction [52.89860691282002]
  Implicit Attribute Value Extraction (AVE) is essential for accurately representing products in e-commerce.<n>Despite advances in multimodal large language models (MLLMs), implicit AVE remains challenging due to the complexity of multidimensional data.<n>We introduce textscmodelname, a multi-agent debate framework that employs multiple MLLM agents to iteratively refine inferences.
  arXiv  Detail & Related papers  (2025-10-07T06:27:42Z)
• ContextualLVLM-Agent: A Holistic Framework for Multi-Turn Visually-Grounded Dialogue and Complex Instruction Following [0.2999888908665658]
  We introduce MMDR-Bench (Multi-Modal Dialogue Reasoning Benchmark), a novel dataset comprising 300 complex multi-turn dialogue scenarios.<n>We also propose CoLVLM Agent (Contextual LVLM Agent), a holistic framework that enhances existing LVLMs with advanced reasoning and instruction following capabilities.<n>Our experiments on MMDR-Bench demonstrate that CoLVLM Agent consistently achieves superior performance, attaining an average human evaluation score of 4.03.
  arXiv  Detail & Related papers  (2025-08-21T02:09:02Z)
• MMCTAgent: Multi-modal Critical Thinking Agent Framework for Complex Visual Reasoning [3.651416979200174]
  MMCTAgent is a novel critical thinking agent framework designed to address the inherent limitations of current MLLMs in complex visual reasoning tasks. Inspired by human cognitive processes and critical thinking, MMCTAgent iteratively analyzes multi-modal information, decomposes queries, plans strategies, and dynamically evolves its reasoning.
  arXiv  Detail & Related papers  (2024-05-28T16:55:41Z)
• Cantor: Inspiring Multimodal Chain-of-Thought of MLLM [83.6663322930814]
  We argue that converging visual context acquisition and logical reasoning is pivotal for tackling visual reasoning tasks. We propose an innovative multimodal CoT framework, termed Cantor, characterized by a perception-decision architecture. Our experiments demonstrate the efficacy of the proposed framework, showing significant improvements in multimodal CoT performance.
  arXiv  Detail & Related papers  (2024-04-24T17:59:48Z)
• Deciphering Digital Detectives: Understanding LLM Behaviors and Capabilities in Multi-Agent Mystery Games [26.07074182316433]
  We introduce the first dataset specifically for Jubensha, including character scripts and game rules. Our work also presents a unique multi-agent interaction framework using LLMs, allowing AI agents to autonomously engage in this game. To evaluate the gaming performance of these AI agents, we developed novel methods measuring their mastery of case information and reasoning skills.
  arXiv  Detail & Related papers  (2023-12-01T17:33:57Z)
• Mastering Robot Manipulation with Multimodal Prompts through Pretraining and Multi-task Fine-tuning [49.92517970237088]
  We tackle the problem of training a robot to understand multimodal prompts. This type of task poses a major challenge to robots' capability to understand the interconnection and complementarity between vision and language signals. We introduce an effective framework that learns a policy to perform robot manipulation with multimodal prompts.
  arXiv  Detail & Related papers  (2023-10-14T22:24:58Z)
• Cooperation, Competition, and Maliciousness: LLM-Stakeholders Interactive Negotiation [52.930183136111864]
  We propose using scorable negotiation to evaluate Large Language Models (LLMs) To reach an agreement, agents must have strong arithmetic, inference, exploration, and planning capabilities. We provide procedures to create new games and increase games' difficulty to have an evolving benchmark.
  arXiv  Detail & Related papers  (2023-09-29T13:33:06Z)

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

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.