Can LLM Teams Play What? Where? When?

• URL: http://arxiv.org/abs/2605.30459v1
• Date: Thu, 28 May 2026 18:36:12 GMT
• Title: Can LLM Teams Play What? Where? When?
• Abstract summary: We investigate whether team-based interaction improves large language models (LLMs) performance in What? Where? When?<n>We introduce three team strategies: Voting, Silent Team (the captain observes final answers), and Talkative Team (the captain observes both answers and rationales)<n>To minimize data leakage, we evaluate these strategies on a dataset consisting of 572 ChGK questions released in 2025.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Large language models (LLMs) remain limited on tasks requiring indirect reasoning, cultural knowledge, and coordinated hypothesis testing. We investigate whether team-based interaction improves LLM performance in What? Where? When? (ChGK), a quiz game designed to reward collective reasoning. We introduce three team strategies: Voting, Silent Team (the captain observes final answers), and Talkative Team (the captain observes both answers and rationales). To minimize data leakage, we evaluate these strategies on a dataset consisting of 572 ChGK questions released in 2025. Using six recent large-scale open models, we show that team-based strategies outperform single-model baselines, yielding gains of up to 20 percentage points in accuracy. The best team achieves 44.23% accuracy, and approaches human team performance on questions with available human statistics. Analysis of inter-model diversity reveals that disagreement strongly predicts lower accuracy, but explanatory communication substantially mitigates performance drops. We further examine captain behavior and find no evidence of self-preference bias; access to peer rationales improves captain judgments. Overall, LLM teams function primarily as answer selection and error-filtering mechanisms rather than generators of novel solutions. Our findings highlight the importance of interaction and suggest adaptive strategies as a promising direction for multi-agent systems.

Related papers

• MINDGAMES: A Live Arena for Evaluating Social and Strategic Reasoning in Multi-Agent LLMs [54.81359054218573]
  We introduce Mindgames, a multi-game arena and evaluation platform for large language models (LLMs)<n>Mindgames provides a unified interaction interface, TrueSkill-based rating, and full trajectory logging across four game environments.<n>We analyze 29,571 multi-agent games with turn-level observations, actions, and rewards, together with MG-Ref, a deterministic offline tournament protocol.
  arXiv  Detail & Related papers  (2026-05-28T07:33:47Z)
• High Volatility and Action Bias Distinguish LLMs from Humans in Group Coordination [3.6704226968275253]
  We compare large language models (LLMs) and human performance on a common-interest game with imperfect monitoring: Group Binary Search.<n>Our findings show that, unlike humans who adapt and stabilize their behavior over time, LLMs often fail to improve across games and exhibit excessive switching.
  arXiv  Detail & Related papers  (2026-04-02T23:21:37Z)
• Shoot First, Ask Questions Later? Building Rational Agents that Explore and Act Like People [81.63702981397408]
  Given limited resources, to what extent do agents based on language models (LMs) act rationally?<n>We develop methods to benchmark and enhance agentic information-seeking, drawing on insights from human behavior.<n>For Spotter agents, our approach boosts accuracy by up to 14.7% absolute over LM-only baselines; for Captain agents, it raises expected information gain (EIG) by up to 0.227 bits (94.2% of the achievable noise ceiling)
  arXiv  Detail & Related papers  (2025-10-23T17:57:28Z)
• Beyond Survival: Evaluating LLMs in Social Deduction Games with Human-Aligned Strategies [54.08697738311866]
  Social deduction games like Werewolf combine language, reasoning, and strategy.<n>We curate a high-quality, human-verified multimodal Werewolf dataset containing over 100 hours of video, 32.4M utterance tokens, and 15 rule variants.<n>We propose a novel strategy-alignment evaluation that leverages the winning faction's strategies as ground truth in two stages.
  arXiv  Detail & Related papers  (2025-10-13T13:33:30Z)
• Staying in the Sweet Spot: Responsive Reasoning Evolution via Capability-Adaptive Hint Scaffolding [59.60915947702282]
  Reinforcement learning with verifiable rewards (RLVR) has achieved remarkable success in enhancing the reasoning capabilities of large language models (LLMs)<n>Existing RLVR methods often suffer from exploration inefficiency due to mismatches between the training data's difficulty and the model's capability.<n>We propose SEELE, a novel supervision-aided RLVR framework that dynamically adjusts problem difficulty to stay within the high-efficiency region.
  arXiv  Detail & Related papers  (2025-09-08T17:36:21Z)
• Mitigating Spurious Correlations Between Question and Answer via Chain-of-Thought Correctness Perception Distillation [25.195244084313114]
  Chain-of-Thought Correctness Perception Distillation (CoPeD) aims to improve the reasoning quality of the student model.<n>CoPeD encourages the student model to predict answers based on correct rationales and revise them when they are incorrect.
  arXiv  Detail & Related papers  (2025-09-06T05:33:17Z)
• Thinkless: LLM Learns When to Think [57.857534644932194]
  Reasoning Language Models, capable of extended chain-of-thought reasoning, have demonstrated remarkable performance on tasks requiring complex logical inference.<n>We propose Thinkless, a learnable framework that empowers an LLM to adaptively select between short-form and long-form reasoning.<n>On several benchmarks such as Minerva Algebra, MATH-500, and GSM8K, Thinkless is able to reduce the usage of long-chain thinking by 50% - 90%.
  arXiv  Detail & Related papers  (2025-05-19T17:24:16Z)
• Improve Vision Language Model Chain-of-thought Reasoning [86.83335752119741]
  Chain-of-thought (CoT) reasoning in vision language models (VLMs) is crucial for improving interpretability and trustworthiness. We show that training VLM on short answers does not generalize well to reasoning tasks that require more detailed responses.
  arXiv  Detail & Related papers  (2024-10-21T17:00:06Z)
• Are Large Language Models Strategic Decision Makers? A Study of Performance and Bias in Two-Player Non-Zero-Sum Games [56.70628673595041]
  Large Language Models (LLMs) have been increasingly used in real-world settings, yet their strategic decision-making abilities remain largely unexplored. This work investigates the performance and merits of LLMs in canonical game-theoretic two-player non-zero-sum games, Stag Hunt and Prisoner Dilemma. Our structured evaluation of GPT-3.5, GPT-4-Turbo, GPT-4o, and Llama-3-8B shows that these models, when making decisions in these games, are affected by at least one of the following systematic biases.
  arXiv  Detail & Related papers  (2024-07-05T12:30:02Z)
• Probing the Multi-turn Planning Capabilities of LLMs via 20 Question Games [14.063311955315077]
  Large language models (LLMs) are effective at answering questions that are clearly asked. When faced with ambiguous queries they can act unpredictably and produce incorrect outputs. This underscores the need for the development of intelligent agents capable of asking clarification questions to resolve ambiguities effectively.
  arXiv  Detail & Related papers  (2023-10-02T16:55:37Z)
• My Team Will Go On: Differentiating High and Low Viability Teams through Team Interaction [17.729317295204368]
  We train a viability classification model over a dataset of 669 10-minute text conversations of online teams. We find that a lasso regression model achieves an accuracy of.74--.92 AUC ROC under different thresholds of classifying viability scores.
  arXiv  Detail & Related papers  (2020-10-14T21:33:36Z)

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.