CEDAR：面向复杂系统目标导向优化的智能体编排树搜索算法
CEDAR: Agent-Orchestrated Tree Search for Goal-Directed Optimization of Complex Systems
浏览论文内容
中文总结 AI 辅助
针对复杂系统目标导向设计的难题，提出基于LLM智能体的CEDAR方法，通过LLM驱动的MCTS实现复杂系统的目标导向发现，减少人力投入并促进其跨领域应用。
中文摘要 AI 辅助
复杂系统是人工生命领域的核心研究对象，通过非线性、反馈驱动的交互作用对各类现象进行建模，产生涌现行为，其应用范围涵盖种群动态、生物学、经济政策及战略决策等诸多领域。然而，预测反馈结构如何产生涌现行为是人工生命领域的核心开放问题，这使得目标导向设计极具挑战性。在现有实践中，系统结构需用DYNAMO或STELLA等专用建模语言编写，繁琐的工作流程进一步加剧了挑战，限制了应用推广并阻碍了及时决策。为解决这些问题，我们提出CEDAR，一种利用大语言模型（LLM）智能体发现满足用户指定行为目标的复杂系统的自主方法。我们的核心创新是与复杂系统深度耦合的LLM驱动蒙特卡洛树搜索（MCTS）：在每次迭代中，LLM评判器（Judge）根据指定目标评估涌现行为，LLM编辑器（Editor）提出改进变体，其中评判器充当适应度函数，编辑器充当变异算子，类似于进化计算中的生成-评估循环。我们将复杂系统表示为带有领域原语的受限可运行Python子集，使LLM能够直接修改系统动力学。CEDAR将此形式化为具有LLM参数化转移核和价值函数的MCTS变体，在保持解多样性的同时实现复杂系统行为的目标导向发现，其基于LLM的可解释性还能揭示结构变化如何驱动涌现行为。CEDAR减少了人力投入，同时具备现有方法难以实现的能力，促进了复杂系统在各领域的更广泛应用。
英文摘要
Complex systems, core objects of study in artificial life, model diverse phenomena through nonlinear, feedback-driven interactions that produce emergent behavior, with applications from population dynamics and biology to economic policy and strategic decision-making. Yet the difficulty of predicting how feedback structure gives rise to emergent behavior, a central open problem in artificial life, makes goal-directed design exceptionally challenging. In established practice, system structures are written in specialized modeling languages such as DYNAMO or STELLA, compounding the challenge with labor-intensive workflows that limit adoption and hinder timely decision-making. To address these challenges, we introduce CEDAR, an autonomous method that uses Large Language Model (LLM) agents to discover complex systems satisfying user-specified behavioral goals. Our key innovation is an LLM-driven Monte Carlo Tree Search (MCTS) deeply coupled with complex systems: at each iteration, an LLM Judge evaluates emergent behavior against specified goals and an LLM Editor proposes improved variants, with the Judge acting as a fitness function and the Editor as a variation operator, akin to a generate-and-evaluate loop in evolutionary computation. We represent complex systems as a restricted, runnable subset of Python with domain-specific primitives, letting LLMs modify system dynamics directly. CEDAR formalizes this as an MCTS variant with an LLM-parameterized transition kernel and value function, enabling goal-directed discovery of complex system behaviors while preserving solution diversity, and its LLM-based interpretability reveals how structural changes drive emergent behavior. CEDAR reduces human effort while enabling capabilities difficult to achieve with existing approaches, facilitating broader adoption of complex systems across domains.
发表机构
- Sakana AI
机构由 AI 辅助整理，请以论文原文为准。
