Large language models (LLMs) have significantly evolved, moving from simple output generation to complex reasoning and from stand-alone usage to being embedded into broader frameworks. In this paper, we introduce \emph{Fleet of Agents (FoA)}, a novel framework utilizing LLMs as agents to navigate through dynamic tree searches, employing a genetic-type particle filtering approach. FoA spawns a multitude of agents, each exploring autonomously, followed by a selection phase where resampling based on a heuristic value function optimizes the balance between exploration and exploitation. This mechanism enables dynamic branching, adapting the exploration strategy based on discovered solutions. We experimentally validate FoA using two benchmark tasks, "Game of 24" and "Mini-Crosswords". FoA outperforms the previously proposed Tree-of-Thoughts method in terms of efficacy and efficiency: it significantly decreases computational costs (by calling the value function less frequently) while preserving comparable or even superior accuracy.

翻译：大语言模型（LLMs）已显著演进，从简单的输出生成发展到复杂推理，并从独立使用转变为嵌入更广泛的框架中。本文提出《智能体舰队》（Fleet of Agents，FoA）这一新颖框架，该框架利用LLMs作为智能体，通过遗传式粒子滤波方法在动态树搜索中导航。FoA生成大量自主探索的智能体，随后进入基于启发式价值函数重采样的选择阶段，以优化探索与利用之间的平衡。该机制实现了动态分支，使探索策略能够根据已发现的解决方案进行自适应调整。我们通过"24点游戏"和"迷你填字游戏"两项基准任务对FoA进行了实验验证。结果表明，FoA在效能与效率上均优于先前提出的"思维树"方法：它显著降低了计算成本（通过减少价值函数的调用频率），同时保持了相当甚至更优的精确度。