cooperative-game-theory

CoGameReg 提出一种基于合作博弈的协同半监督回归框架，利用 Tri-Game Shapley 机制为异构回归器加权并构建共享伪标签，用于稀疏井标签条件下的地震储层属性预测，并在基准数据集与油田盲井验证中取得更优表现。

This paper formalizes agent coalition formation and inter-agent communication as a cooperative game, proposing marginal-value activation rules and Shapley-based online routing to reduce token costs and improve efficiency in multi-agent LLM systems, with theoretical guarantees and synthetic simulation results.

This paper introduces Shapley Context Pruning (SCP), a cooperative game-theoretic framework for context reranking and pruning in RAG systems. It employs a Deep Sets architecture and Monte-Carlo sampling to efficiently attribute importance to sentences, achieving competitive downstream QA performance with a lightweight 3M-parameter value network.