arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2501.18668cs.AIcs.SE
收藏

Simulation Streams:一种用于控制大型语言模型并利用生成式AI构建复杂系统的编程范式

Simulation Streams: A Programming Paradigm for Controlling Large Language Models and Building Complex Systems with Generative AI

Google DeepMind(谷歌DeepMind)

Peter Sunehag, Joel Z. Leibo

AI总结:

Simulation Streams是一种编程范式,通过基于状态和ECS架构的方法控制LLMs,解决其在复杂动态模拟和智能体工作流中的一致性、信息过滤和规则执行问题,支持多实体模拟并保持模块化与一致性。

摘要:

我们介绍了Simulation Streams,这是一种编程范式,旨在高效地控制和利用大型语言模型(LLMs)进行复杂的动态模拟和智能体工作流。我们的主要目标是创建一个最小干扰的框架,利用LLMs的智能体能力,同时解决其在保持一致性、选择性忽略/包含信息以及强制执行严格世界规则方面的局限性。Simulation Streams通过基于状态的方法实现这一目标,其中变量在连续步骤中被“操作符”修改,以重复格式产生输出,并遵循状态变量的一致规则。这种方法将LLMs集中在定义的任务上,同时旨在使上下文流保持“分布内”。该方法结合了实体-组件-系统(ECS)架构,以更直观的方式编写程序,促进不同组件和实体之间工作流的重用。这种ECS方法增强了输出流的模块化,允许进行复杂的多实体模拟,同时保持格式一致性、信息控制和规则执行。它由一个自定义编辑器支持,帮助创建、运行和分析模拟。我们通过一个正在进行的市场经济模拟的说明性示例、三个角色在公园玩接球游戏的社会模拟以及一套经典强化学习基准任务,展示了Simulation Streams的多功能性。这些示例展示了Simulation Streams处理复杂、不断演变的场景在100到1000次迭代中的能力,促进不同智能体工作流和模型之间的比较,并在LLM驱动的模拟中保持一致性和持续有趣的发展。

英文摘要:

We introduce Simulation Streams, a programming paradigm designed to efficiently control and leverage Large Language Models (LLMs) for complex, dynamic simulations and agentic workflows. Our primary goal is to create a minimally interfering framework that harnesses the agentic abilities of LLMs while addressing their limitations in maintaining consistency, selectively ignoring/including information, and enforcing strict world rules. Simulation Streams achieves this through a state-based approach where variables are modified in sequential steps by "operators," producing output on a recurring format and adhering to consistent rules for state variables. This approach focus the LLMs on defined tasks, while aiming to have the context stream remain "in-distribution". The approach incorporates an Entity-Component-System (ECS) architecture to write programs in a more intuitive manner, facilitating reuse of workflows across different components and entities. This ECS approach enhances the modularity of the output stream, allowing for complex, multi-entity simulations while maintaining format consistency, information control, and rule enforcement. It is supported by a custom editor that aids in creating, running, and analyzing simulations. We demonstrate the versatility of simulation streams through an illustrative example of an ongoing market economy simulation, a social simulation of three characters playing a game of catch in a park and a suite of classical reinforcement learning benchmark tasks. These examples showcase Simulation Streams' ability to handle complex, evolving scenarios over 100s-1000s of iterations, facilitate comparisons between different agent workflows and models, and maintain consistency and continued interesting developments in LLM-driven simulations.

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。

↑