{"total":21,"rows":[{"id":"2505.09990","title":"PointArena: Probing Multimodal Grounding Through Language-Guided Pointing","created":"2025-05-15","cited_by_count":31,"area":null},{"id":"2502.09053","title":"Game Theory Meets Large Language Models: A Systematic Survey with Taxonomy and New Frontiers","created":"2025-02-13","cited_by_count":16,"area":null},{"id":"2512.09187","title":"WOLF: Werewolf-based Observations for LLM Deception and Falsehoods","created":"2025-12-09","cited_by_count":13,"area":null},{"id":"2510.11389","title":"Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies","created":"2025-10-13","cited_by_count":10,"area":null},{"id":"2509.23023","title":"Deceive, Detect, and Disclose: Large Language Models Play Mini-Mafia","created":"2025-09-27","cited_by_count":9,"area":null},{"id":"2412.04937","title":"Who Speaks Next? Multi-party AI Discussion Leveraging the Systematics of Turn-taking in Murder Mystery Games","created":"2024-12-06","cited_by_count":7,"area":null},{"id":"2602.03109","title":"One Model, All Roles: Multi-Turn, Multi-Agent Self-Play Reinforcement Learning for Conversational Social Intelligence","created":"2026-02-03","cited_by_count":7,"area":null},{"id":"2605.30094","title":"PokerSkill: LLMs Can Play Expert-Level Poker without Training or Solvers","created":"2026-05-28","cited_by_count":5,"area":null},{"id":"2605.09965","title":"Towards Generalist Game Players: An Investigation of Foundation Models in the Game Multiverse","created":"2026-05-11","cited_by_count":3,"area":null},{"id":"2505.20120","title":"Agents Require Metacognitive and Strategic Reasoning to Succeed in the Coming Labor Markets","created":"2025-05-26","cited_by_count":2,"area":null},{"id":"2507.12732","title":"Strategy Adaptation in Large Language Model Werewolf Agents","created":"2025-07-17","cited_by_count":2,"area":null},{"id":"2509.17192","title":"Shall We Play a Game? Language Models for Open-ended Wargames","created":"2025-09-21","cited_by_count":2,"area":null},{"id":"2511.10691","title":"Evaluating from Benign to Dynamic Adversarial: A Squid Game for Large Language Models","created":"2025-11-12","cited_by_count":2,"area":null},{"id":"2601.13709","title":"Hidden in Plain Text: Measuring LLM Deception Quality Against Human Baselines Using Social Deduction Games","created":"2026-01-20","cited_by_count":2,"area":null},{"id":"2605.22826","title":"Evaluating Large Language Models in a Complex Hidden Role Game","created":"2026-04-09","cited_by_count":1,"area":null},{"id":"2606.13310","title":"RogueAI: A Reverse Turing Test for Detecting Licensed AI Deception in Dialogue","created":"2026-06-11","cited_by_count":1,"area":null},{"id":"2601.09017","title":"Multicultural Spyfall: Assessing LLMs through Dynamic Multilingual Social Deduction Game","created":"2026-01-13","cited_by_count":0,"area":null},{"id":"2606.27909","title":"Triadic Werewolf: A Jester Role for Multi-Hop Theory of Mind in LLMs","created":"2026-06-26","cited_by_count":0,"area":null},{"id":"2608.08199","title":"Persuasive and Compliant Tendencies Predict Group Decision-Making in Humans and Language Models","created":"2026-08-08","cited_by_count":0,"area":null},{"id":"2610.04261","title":"Playing social deduction games with reinforcement fine-tuned large language models","created":"2026-10-03","cited_by_count":0,"area":null},{"id":"2610.05041","title":"Communication Shapes Collective Inference in Self-Adapting LLM Societies: Evidence from Mafia","created":"2026-10-04","cited_by_count":0,"area":null}],"next_cursor":null}