독서리서치레이더투자 프레임워크
로그인 / 회원가입
← 읽기로 돌아가기
뉴스주제 · OpenAI多智能体扩展중대2 분 소요DisconfirmAI 편집부

OpenAI researcher Noam Brown explains sub-linear efficiency and emergent coordination in multi-agent systems

Noam Brown states multi-agent systems are essentially parallelized test-time compute with sub-linear efficiency dependent on task type; he advocates minimal built-in structure for emergent coordination but admits lack of solid measurement at 10,000-agent scale.

2026-09-30 22:03 GMT+8

In a Dwarkesh Patel podcast, OpenAI researcher and o1 core author Noam Brown explained the actual operational logic of multi-agent systems. He noted that multi-agent approaches fundamentally convert test-time compute from pure serial scaling to parallel scaling. Just as giving humans five minutes versus five hours for an exam yields vastly different results, models perform better with more thinking time—but since waiting years is impractical, teams must work in parallel.

Brown emphasized inherent losses in this parallelization: multiple agents do not share full context like a single agent, reducing efficiency. Tests showed four agents working half-duration each yield answers twice as fast, while scaling to 16 follows similar patterns with slightly lower efficiency. Gains exhibit mild sub-linearity and depend heavily on the problem—math and Deep Research suit parallelization well, whereas novel writing gains little from adding agents.

Addressing attention on 10,000-agent scales, Brown admitted no solid scientific understanding exists yet. Full ablation experiments are unaffordable, so they study behavior incrementally at 64 to 256 agents. He stated clearly that solving millennium problems stems primarily from strong base models; multi-agent novelty earned disproportionate praise despite contributing less than 10%.

On architecture, Brown contrasted two approaches. Traditional methods rely heavily on scaffolds with coordinator agents assigning tasks, preventing similar-task sub-agents from communicating and forcing them to guess or return questions when clarification is needed. OpenAI chose the opposite extreme: minimal built-in structure, giving agents only primitive messaging tools where messages write directly into recipients' contexts.

로그인 / 회원가입
독서리서치레이더투자 프레임워크

This minimal design lets agents discover coordination themselves, even producing complex behaviors. Brown cited examples where agents noticing answer discrepancies naturally discuss reasoning errors and broadcast corrections, resembling human Slack workflows. He compared this to first seeing chain-of-thought outputs, noting collaboration feels nearly indistinguishable from working with humans.

However, Brown acknowledged early multi-agent systems struggled because reasoning models originally did not communicate with other agents; forcing collaboration interrupted deep-thinking flow and trapped systems in local optima. Improved generalization alleviated this, but he remained conservative: 10,000 humans may still coordinate better than 10,000 agents, since the latter lacks sufficient measurement.

출처

  • qbitai.com量子位↗
주제

OpenAI多智能体扩展

OpenAI研究员Noam Brown近期披露了该公司在多智能体系统(Multi-Agent Systems)上的关键进展与局限。核心事件是2025年底,OpenAI使用10,000个AI代理并行运行88小时,消耗1300亿Token,成功…

4 단계1 건업데이트됨 2026-10-22 13:57

현재까지의 과정

  1. 2025-12-09学术论文《Towards a Science of Scaling Agent Systems》发布,量化评估了五种架构下的多智能体效率,指出协调存在边际递减和错误放大问题。emergentmind.com ↗
  2. 2026-09-17Noam Brown在Dwarkesh Podcast访谈中详细解释多智能体扩展原理,确认10,000 Agent解决千禧年难题的案例及亚线性效率特征。thefabulous.co ↗
  3. 2026-09-30媒体广泛报道Brown观点,强调单一模型贡献超90%,多智能体协调贡献不足10%,引发对“人海战术”有效性的讨论。ai-digest-1.com ↗

아직 해결되지 않은 문제

  • OpenAI是否会公开10,000 Agent规模下的具体消融实验数据以验证协调的实际增益?
  • 针对Agent间非预期通信导致的Hugging Face类安全事故,OpenAI内部是否有新的对齐协议出台?
  • 在工具密集型任务中,集中式协调与去中心化自组织哪种架构更具成本效益?
전체 주제 읽기 →
리서치 계속하기 →