mirror of
https://github.com/hanzoai/papers.git
synced 2026-10-29 07:34:31 +00:00
zeekay
0f01f8b555
Resolves high-severity review findings: anachronistic dates aligned to citation floors; arithmetic corrected to match formulas; internal contradictions collapsed to the body-supported value; LP self-references aligned to filenames; liquidity-surface repo paths scrubbed; AI-slop trimmed. PDFs rebuilt separately.
62 lines
2.5 KiB
TeX
62 lines
2.5 KiB
TeX
\documentclass[11pt,twocolumn]{article}
|
|
\usepackage{../shared/hanzocover}
|
|
\usepackage[utf8]{inputenc}
|
|
\usepackage{amsmath,amssymb,amsthm}
|
|
\usepackage{graphicx}
|
|
\usepackage{booktabs}
|
|
\usepackage{algorithm}
|
|
\usepackage{algorithmic}
|
|
\usepackage{hyperref}
|
|
\usepackage{xcolor}
|
|
\usepackage{listings}
|
|
\input{../shared/lstlang}
|
|
\usepackage{tikz}
|
|
\usetikzlibrary{shapes,arrows,positioning,fit,backgrounds}
|
|
|
|
\definecolor{codegreen}{rgb}{0,0.6,0}
|
|
\definecolor{codegray}{rgb}{0.5,0.5,0.5}
|
|
\definecolor{codepurple}{rgb}{0.58,0,0.82}
|
|
\definecolor{backcolour}{rgb}{0.95,0.95,0.92}
|
|
|
|
\lstdefinestyle{mystyle}{
|
|
backgroundcolor=\color{backcolour},
|
|
commentstyle=\color{codegreen},
|
|
keywordstyle=\color{codepurple},
|
|
numberstyle=\tiny\color{codegray},
|
|
stringstyle=\color{codegreen},
|
|
basicstyle=\ttfamily\footnotesize,
|
|
breakatwhitespace=false,
|
|
breaklines=true,
|
|
captionpos=b,
|
|
keepspaces=true,
|
|
numbers=left,
|
|
numbersep=5pt,
|
|
showspaces=false,
|
|
showstringspaces=false,
|
|
showtabs=false,
|
|
tabsize=2
|
|
}
|
|
\lstset{style=mystyle}
|
|
|
|
\title{Hanzo Agent SDK: Building AI Agents with Orchestration, Tool Use, and Memory Systems}
|
|
\author{Antje Worring, Zach Kelling\thanks{[email protected]} \\ \textit{Hanzo Industries \quad Lux Industries \quad Zoo Labs Foundation} \\ \texttt{[email protected]}}
|
|
\date{February 2024}
|
|
|
|
\begin{document}
|
|
|
|
\hanzocoverpage
|
|
|
|
\begin{abstract}
|
|
We present Hanzo Agent SDK, a multi-agent orchestration framework that unifies agent execution, tool management, and memory systems under a single, extensible architecture. The framework introduces three key innovations: (1) a generic Agent dataclass with support for dynamic instructions, typed contexts, and composable guardrails; (2) a hierarchical memory system with semantic retrieval, automatic compression, and reflection capabilities; and (3) an AgentNetwork abstraction enabling parallel execution, shared state management, and intelligent routing between specialized agents. We demonstrate that multi-agent orchestration with semantic routing achieves 34\% higher task completion rates compared to single-agent approaches on complex, multi-step reasoning benchmarks. The SDK is designed for production deployment with comprehensive tracing, lifecycle hooks, and Model Context Protocol (MCP) integration.
|
|
\end{abstract}
|
|
|
|
\input{sections/01-introduction}
|
|
\input{sections/02-background-and-related-work}
|
|
\input{sections/03-architecture}
|
|
\input{sections/04-implementation-details}
|
|
\input{sections/05-evaluation}
|
|
\input{sections/06-discussion}
|
|
\input{sections/99-conclusion}
|
|
|
|
\end{document}
|