---
title: "Interview | DeepWisdom (MetaGPT) CEO Chenglin Wu: Multi-Agents Redefining Code Generation"
author: "Unique Research"
sourcePublication: "Unique Research (FFCAP English library)"
originalPublishedAt: "2024-11-15T11:15:00+08:00"
canonical: "https://ffcap.cn/en/research/20241115a03fvu00"
source: "https://ffcap.cn/en/research/20241115a03fvu00"
language: "en"
cnSourceUrl: "https://view.inews.qq.com/a/20241115A03FVU00"
---

# Interview | DeepWisdom (MetaGPT) CEO Chenglin Wu: Multi-Agents Redefining Code Generation

_Unique Research · Interview · November 15, 2024_

At Unique Capital’s AIGC Application Development Summit & AIGC100 Awards in Beijing (Oct 17, 2024) — 50+ speakers, ~1,000 practitioners — DeepWisdom founder & CEO **Chenglin Wu** delivered “Multi-Agents Leading a New Exploration of Code Generation.” Edited highlights:

## LLMs + agents democratize natural-language programming

Software — whether frontier LLMs or classic NLP — faces four global pain points:

1.  **Hard to code** — many languages (Java, Python, C++…), DS&A, distributed systems for big data.
2.  **Long cycles** — requirements → design → code → test; each stage costly.
3.  **Expensive talent** — >27M programmers globally (→~28M in 2024); total hire cost >$2.79T (~$99k/person-year average).
4.  **High barriers** — IT outsourcing market ~$52.5B / outsourcing services ~$66.5B. GitHub Copilot can cut programming-related cost by up to ~90% via generation and routine automation.

Natural-language programming is getting funded: Poolside (ex-GitHub CTO) raised **$500M seed** at **$3B** valuation (eBay Ventures, Nvidia et al.). Copilot: 1M paid subs by Oct 2023; GitHub 2024 revenue expected ~$2B with Copilot >40% of growth.

## Multi-agents lift LLM performance

Classic agent = observes & acts on environment — too thin; agents should exceed human mistakes (e.. autonomous driving). Analogy: LLM ≈ cognition (language/image/sound); cognition ≠ full reasoning — agents add observe / think / act / memory, trained in environments. Multi-agent systems add agents, environment, SOPs, review, routing, subscription, economic mechanisms.

**MetaGPT** (DeepWisdom, open-sourced Jun 2023): first multi-agent NL programming framework — **40K GitHub stars** by Sep 2024; repeated #1 GitHub Trending. Data Interpreter drew Andrew Ng’s attention. Automates docs and roles (PM → architect → eng → QA) via SOPs + metaprogramming to fight LLM hallucination on project-scale codegen. Internal experiments (Python games, CRUD, simple analytics): average score **3.9**, beating peer auto tools.

## Representative cases

**Android Agent:** learning framework so agents acquire tap/swipe/long-press/double-tap semantics across icons without prior phone experience.

**MetaGPT X (academic):** multi-agent software problem-solving — **46.67%** solve rate with advanced code understanding/debug. Open-sourced **AFLOW**: MCTS auto-optimizes agentic workflows (nodes/edges + operators) — **+5.7%** vs hand design; better performance at **4.55%** of GPT-4o cost. Workflows as “thought guidance” can yield o1-like effects.

**Data Interpreter:** with university partners — hierarchical graph dynamic planning, tool integration/generation, confidence + experience-driven reasoning. SOTA: MATH +26% accuracy; ML-Benchmark 0.86→0.95; open-ended tasks **+112%**. Experience reuse cuts cost after first solve.

**SELA auto-experiment system:** LLM + MCTS for AutoML — on 20 datasets, win rate **65–80%** above prior methods.

## Closing

Ultimate multi-agent form? Org design matters (Tencent/Alibaba/Huawei vs Amazon/Microsoft/Google; Apple’s centralization also works). Thousands of companies build agents — will they form networks like humans on WeChat? Wu: agent nets inside every company, phone, car — different functions that compose into an ecosystem.

— END —

---

Editorial English edition published on UniqueCapital: https://ffcap.cn/en/research/20241115a03fvu00
On-site reading page: https://ffcap.cn/en/research/20241115a03fvu00