通过分析大模型协作中的化学效应，推荐更优组合。
LLM Chemistry Estimation for Multi-LLM Recommendation
- 定义并量化大模型协作时的协同/冲突关系
- 在分类、摘要等任务中验证协作效果受任务类型影响
- 适合需要优化多模型集成的AI系统开发者
多大模型协作有望实现精准、鲁棒且上下文感知的解决方案，但现有方法依赖隐式选择与输出评估，未分析协作模型是否真正互补或冲突。我们提出LLM Chemistry——一种衡量大模型组合是否存在协同或对抗行为的框架，该行为会超越单个模型能力影响整体表现。通过形式化大模型间的化学概念，设计算法分析交互依赖性以量化化学效应，并据此推荐最优模型集合。理论分析表明，异质模型配置下化学效应最显著，其影响由任务类型、组大小和复杂度决定。在分类、摘要和程序修复任务上的评估初步验证了任务依赖性效应，支持理论结论。这使LLM Chemistry成为多大模型系统的重要诊断工具和集成推荐基础。
原文摘要 · Abstract (English)
Multi-LLM collaboration promises accurate, robust, and context-aware solutions, yet existing approaches rely on implicit selection and output assessment without analyzing whether collaborating models truly complement or conflict. We introduce LLM Chemistry -- a framework that measures when LLM combinations exhibit synergistic or antagonistic behaviors that shape collective performance beyond individual capabilities. We formalize the notion of chemistry among LLMs, propose algorithms that quantify it by analyzing interaction dependencies, and recommend optimal model ensembles accordingly. Our theoretical analysis shows that chemistry among collaborating LLMs is most evident under heterogeneous model profiles, with its outcome impact shaped by task type, group size, and complexity. Evaluation on classification, summarization, and program repair tasks provides initial evidence for these task-dependent effects, thereby reinforcing our theoretical results. This establishes LLM Chemistry as both a diagnostic factor in multi-LLM systems and a foundation for ensemble recommendation.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。