LLM 团队能玩“什么？哪里？何时？”吗？
Can LLM Teams Play What? Where? When?
AI总结：
本文研究基于团队的交互策略（投票、静默团队、健谈团队）能否提升大语言模型在“什么？哪里？何时？”问答游戏中的表现，实验表明团队策略优于单模型基线，准确率最高提升20个百分点，最佳团队达到44.23%，接近人类水平。
摘要：
大语言模型（LLM）在需要间接推理、文化知识和协调假设测试的任务上仍然受限。我们研究基于团队的交互是否能提升LLM在“什么？哪里？何时？”（ChGK）问答游戏中的表现，该游戏旨在奖励集体推理。我们引入了三种团队策略：投票、静默团队（队长观察最终答案）和健谈团队（队长观察答案和理由）。为最小化数据泄露，我们在2025年发布的572个ChGK问题数据集上评估这些策略。使用六个近期的大规模开源模型，我们表明基于团队的策略优于单模型基线，准确率提升高达20个百分点。最佳团队达到44.23%的准确率，并在有人类统计数据的题目上接近人类团队表现。模型间多样性分析显示，分歧强烈预测较低准确率，但解释性沟通显著缓解性能下降。我们进一步检查队长行为，未发现自我偏好偏差的证据；访问同伴理由提升了队长判断。总体而言，LLM团队主要作为答案选择和错误过滤机制，而非新解决方案的生成器。我们的发现强调了交互的重要性，并表明自适应策略是多智能体系统的一个有前景的方向。
英文摘要：
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.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
