How Agents Fix Each Other #Shorts

From the paper: Self-Evolving Multi-Agent Swarms.

Abstract
We present LocalKin, a self-evolving multi-agent swarm architecture capable of autonomously auditing, repairing, and verifying its own constituent agents without human intervention. The system runs 78 specialized agents on a single consumer machine (16GB Mac Mini) with a total memory footprint of 960MB---approximately 12.5MB per agent---compared to 200MB or more per agent in Python-based frameworks such as AutoGen and CrewAI. The core contribution is a fully autonomous improvement loop consisting of four stages: quality audit, feedback synthesis, targeted repair, and verification. Over a continuous 5-day autonomous deployment, the system completed more than 30 improvement cycles, autonomously modified 68 agent configuration files, and discovered, evaluated, and integrated techniques from 6 research papers found on arXiv and HuggingFace---all with zero human intervention. Compliance scores improved from approximately 75% on day one to 92% by day five, while hallucination incidents dropped from four in the first two days to zero in the final two. These results demonstrate that Harness Engineering principles---constraints, feedback, and verification---can be fully automated at swarm scale, producing a system that does not merely execute tasks but continuously improves its own quality, safety, and capability.
Keywords: multi-agent systems, self-evolution, autonomous improvement, swarm intelligence, quality assurance, harness engineering

这篇文章介绍了一种名为 LocalKin 的自进化多智能体集群架构，该系统通过“瘦灵魂、胖技能”的设计，实现了在单台消费级电脑上高效运行 78 个低内存占用的 AI 智能体。其核心贡献在于建立了一个完全自主的质量审计与修复闭环，使系统能够无需人类干预，便能通过审计、反馈、修理和验证四个阶段持续优化自身的配置与合规性。在为期五天的实测中，该集群展现了惊人的自主学习能力，不仅显著提升了任务合规率并消除了幻觉，还通过抓取学术论文自主集成新技术，将“马具工程”的可靠性原则从理论转化为大规模自动化实践。这种架构标志着 AI 开发重心的转移：相比于精雕细琢单个提示词，构建一个能够自我迭代和自我修复的基础设施对于生产级 AI 系统而言更具价值。

Full paper: https://localkin.dev/papers/self-evolving-swarms
GitHub: https://github.com/LocalKinAI/localkin

#LocalKin #AIAgents #Shorts

Видео How Agents Fix Each Other #Shorts канала LocalKinAI