arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2607.01047cs.CL
收藏

可对话的复杂性:作为可解释基质的智能体LLM集体

Conversable Complexity: Agentic LLM Collectives as Interpretable Substrates

IT University of Copenhagen(哥本哈根信息技术大学);University of Oslo(奥斯陆大学);Østfold University of Applied Sciences(东福尔应用科学大学);Sakana AI

Elias Najarro, Ane Espeseth, Eleni Nisioti, Sebastian Risi, Stefano Nichele

AI总结:

本文提出将智能体大语言模型集体作为人工生命研究的计算基质,利用自然语言通信实现可解释性,并综述了相关实例。

摘要:

复杂性和可解释性很少同时出现:足以产生复杂行为的系统通常过于不透明而无法质疑,而透明的系统又过于简单而无法产生任何复杂现象。单个大语言模型(LLM)是一个静态产物,几乎不表现出任何与生命相关的涌现特性。通过交互,这种情况发生了变化:LLM群体展现出孤立模型所不具备的涌现动力学。此外,LLM可以被赋予持久记忆、工具和共享技能,以及主动发起行动的能力,即让LLM具有智能体特性。在本文中,我们认为这种智能体集体可以作为人工生命(ALife)研究的计算基质。关键在于,由于智能体使用自然语言进行通信,它们的集体行为可以通过检查文本痕迹和直接询问智能体本身来进行直接探究。我们概述了语言模型研究中的可解释性概念,并将其扩展到智能体集体。最后,我们调查了近期已经实例化智能体基质概念的智能体LLM集体实例,从受控实验到实际部署。

英文摘要:

Complexity and interpretability rarely coincide: systems rich enough for complex behaviours to emerge are usually too opaque to question, while transparent ones are too simple for anything complex to emerge. A single large language model (LLM) is a static artefact, hardly exhibiting any of the emergent properties we associate with life. This changes through interaction: populations of LLMs display emergent dynamics absent from isolated models. Furthermore, LLMs can be endowed with persistent memory, tools and shared skills, and the capacity to initiate actions unprompted, i.e., turning LLMs agentic. In this paper, we argue that such collectives of agents can serve as a computational substrate for Artificial Life (ALife) research. Critically, since the agents communicate in natural language, their collective behaviour can be directly interrogated by examining textual traces and asking the agents themselves. We outline the notion of interpretability in language-model research and extend it for collectives of agents. Lastly, we survey recent examples of agentic LLM collectives that already instantiate the idea of agentic substrates, from controlled experiments to deployments in the wild.

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。

↑