通过语言游戏实现自我迭代，让智能体无限提升能力
Boundless Socratic Learning with Language Games
- 用语言游戏构建闭环反馈，驱动智能体自我进化
- 理论上可突破初始数据限制，性能随时间持续增长
- 适合研究通用智能与自进化系统的人参考
在封闭系统中，只要满足三个条件：（a）获得充分信息且对齐的反馈，（b）具备足够广泛的经验覆盖，（c）拥有充足容量与资源，智能体便可掌握任意所需能力。本文论证这些条件的必要性，分析当（c）非瓶颈时，（a）和（b）带来的局限。针对输入输出空间一致（即语言）的智能体，我们提出‘苏格拉底式学习’——一种纯递归自我改进机制，能使其性能远超初始数据所限，仅受时间和渐进偏差影响。此外，我们基于语言游戏概念，提出一个可实现该机制的构造性框架。
原文摘要 · Abstract (English)
An agent trained within a closed system can master any desired capability, as long as the following three conditions hold: (a) it receives sufficiently informative and aligned feedback, (b) its coverage of experience/data is broad enough, and (c) it has sufficient capacity and resource. In this position paper, we justify these conditions, and consider what limitations arise from (a) and (b) in closed systems, when assuming that (c) is not a bottleneck. Considering the special case of agents with matching input and output spaces (namely, language), we argue that such pure recursive self-improvement, dubbed "Socratic learning", can boost performance vastly beyond what is present in its initial data or knowledge, and is only limited by time, as well as gradual misalignment concerns. Furthermore, we propose a constructive framework to implement it, based on the notion of language games.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。