mlsanityData to 7 Oct 2026

Enhancing Consistency of Werewolf AI through Dialogue Summarization and Persona Information

arXiv 2603.07111 ↗First posted 7 Mar 2026cs.CL cs.AIcited by 1

Not on the map. Why?

Abstract (arXiv)

The Werewolf Game is a communication game where players' reasoning and discussion skills are essential. In this study, we present a Werewolf AI agent developed for the AIWolfDial 2024 shared task, co-hosted with the 17th INLG. In recent years, large language models like ChatGPT have garnered attention for their exceptional response generation and reasoning capabilities. We thus develop the LLM-based agents for the Werewolf Game. This study aims to enhance the consistency of the agent's utterances by utilizing dialogue summaries generated by LLMs and manually designed personas and utterance examples. By analyzing self-match game logs, we demonstrate that the agent's utterances are contextually consistent and that the character, including tone, is maintained throughout the game.

Key facts. Cited by 1 paper in the map (data through 7 Oct 2026). Builds on 13 of its 26 references that are in the map. First posted on arXiv 7 Mar 2026.

Builds on

13 of 26 references.

References · 13

  1. 2020Language Models are Few-Shot Learnerscited by 32,199
  2. 2022Large Language Models are Zero-Shot Reasonerscited by 4,323
  3. 2018Personalizing Dialogue Agents: I have a dog, do you have pets too?cited by 820
  4. 2019SAMSum Corpus: A Human-annotated Dialogue Dataset for Abstractive Summarizationcited by 530
  5. 2022Precise Zero-Shot Dense Retrieval without Relevance Labelscited by 508
  6. 2021QMSum: A New Benchmark for Query-based Multi-domain Meeting Summarizationcited by 363
  7. 2023Character-LLM: A Trainable Agent for Role-Playingcited by 335
  8. 2022Social Simulacra: Creating Populated Prototypes for Social Computing Systemscited by 300
  9. 2023Exploring Large Language Models for Communication Games: An Empirical Study on Werewolfcited by 238
  10. 2016A Persona-Based Neural Conversation Modelcited by 221
  11. 2023Large Language Models as Zero-Shot Conversational Recommenderscited by 126
  12. 2021MediaSum: A Large-scale Media Interview Dataset for Dialogue Summarizationcited by 104
1 more
  1. 2022Counseling Summarization using Mental Health Knowledge Guided Utterance Filteringcited by 18

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 1.

1 paper.

  1. 2026Can Agents Deceive? Evaluating Reasoning and Deception in ParliamentBench using a Social Deduction Gamecited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2024An Implementation of Werewolf Agent That does not Truly Trust LLMs
  2. 2025Verbal Werewolf: Engage Users with Verbalized Agentic Werewolf Game Framework
  3. 2025WereWolf-Plus: An Update of Werewolf Game setting Based on DSGBench
  4. 2023Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game
  5. 2024Enhance Reasoning for Large Language Models in the Game Werewolf
  6. 2025MultiMind: Enhancing Werewolf Agents with Multimodal Reasoning and Theory of Mind
  7. 2025Learning Strategic Language Agents in the Werewolf Game with Iterative Latent Space Policy Optimization
  8. 2024Helmsman of the Masses? Evaluate the Opinion Leadership of Large Language Models in the Werewolf Game