AI 与机器学习2025arxiv.org
只有智能体还不够（Agents Are Not Enough）
Agents Are Not Enough
入门 · 约 20 分钟读完前置知识：AI 智能体概念、LLM 应用基础
导读
这篇论文《Agents Are Not Enough》探讨了 AI 智能体（agents）的定位问题，认为单靠智能体本身不足以解决实际任务。论文开篇给出了一个极宽泛的智能体定义——从根据传感器调节温度的恒温器到自动驾驶汽车都算智能体，并在此基础上讨论智能体能力的局限。
HN 关注点：是因为「AI agents」是当前热门概念，但定义混乱、期望过高，讨论焦点集中在智能体的定义边界以及 LLM 智能体是否被过度炒作。
HN 评论精选
这几条评论里：支持 1 质疑 1 补充 2
质疑论文采用的智能体定义过于宽泛，从恒温器到自动驾驶都算，凸显了该术语定义混乱的问题。
这篇论文至少开篇就给出了它对「智能体」的定义（我很恼火人们谈论 agents 时从不澄清用的是众多定义中的哪一个）：AI 语境下的智能体是从用户那里获取偏好、指令等输入、代其完成特定任务的自主实体或程序，范围可以从根据传感器读数调节温度的恒温器，到在车流中导航的自动驾驶汽车。这几乎是最宽泛的定义，把恒温器到 Waymo 全都涵盖了。
simonw查看英文原文
This paper does at least lead with its version of what "agents" means (I get very frustrated when people talk about agents without clarifying which of the many potential definitions they are using): > An agent, in the context of AI, is an autonomous entity or program that takes preferences, instructions, or other forms of inputs from a user to accomplish specific tasks on their behalf. Agents can range from simple systems, such as thermostats that adjust ambient temperature based on sensor readings, to complex systems, such as autonomous vehicles navigating through traffic. This appears to be the broadest possible definition, encompassing thermostats all the way through to Waymos.
支持LLM 不会是通往 AGI 的银弹，未来应是能按问题选择合适模型的专家混合系统。
我做过 CNN、GNN 等传统 AI 方法，也偶尔把玩 LLM。如果 AGI/超级智能可能实现——这只是个假设——我不认为 LLM 会是银弹。就像现实中律师、医生、脑外科医生各自专精一域，我认为最好的路径是「专家混合」：LLM 擅长 NLP 类问题，但它永远不会造出像 Stockfish 那样的模型。不同模型适合不同类型的问题，真正的 AGI 不该试图精通一切，而是知道对给定问题该用哪种方法/模型。把所有希望押在单一方案上是愚蠢的。
tonetegeatinst查看英文原文
Somewhat related but here's my take on super intelligence or AGI. I have worked with CNN,GNN and other old school AI methods, but don't have the resources to build a real SOT LLM, but I do use and tinker with LLM's occasionally. If AGI or SI(super intelligence)/is possible, and that is an if...I don't think LLM's are going to be this silver bullet solution Just as we have in the real world of people who are dedicated to a single task in their field like a lawyer or construction workers or doctors and brain surgeons, I see the current best path forward as being a "mixture of experts". We know LLM's are pretty good for what iv seen some refer to as NLP problems, where the model input is the tokenized string input. However I would argue an LLM will never built a trained model like stockfish or deepseek. Certain model types seem to be suited to certain issues/types of problems or inputs. True AGI or SI would stop trying to be a grand master of everything but rather know what best method/model should be applied to a given problem. We still do not know if it is possible to combine the knowledge of different types of neural networks like LLMs, convolutional neural networks, and deep learning...and while its certainly worth exploring, it is foolish to throw all hope on a single solution approach. I think the first step would be to create a new type of model where given a problem of any type. It knows the best method to solve it. And it doesn't rely on itself but rather the mixture of agents or experts. And they don't even have to be LLMs. They could be anything. Where this really would explode is, if the AI was able to identify a problem that it can't solve and invent or come up with a new approach, multiple approaches, because we don't have to be the ones who develop every expert.
补充与其做自主智能体，不如把 LLM 当作用户操作系统的界面，由人保持在回路中纠错。
我认为最稳妥的路径是让用户自己充当智能体，把 LLM 仅作为操作系统的 UI/UX。人在回路（领域专家）能在幻觉彻底失控前提供合理的纠错机会。「LLM 作为 UI」是个唾手可得的机会：与其花几个月折腾复杂的管理后台和 Web 框架，不如把底层 CRUD 方法直接接进 LLM 提示回调，甚至可以让 LLM 成为管理下一个 SaaS 产品的唯一界面，而且可以做到像传统表单应用一样健壮和安全。
bob1029查看英文原文
I think the goldilocks path is to make the user the agent and use the LLM simply as their UI/UX for working with the system. Human (domain expert) in the loop gives you a reasonable chance of recovering from hallucinations before they spiral entirely out of control. "LLM as UI" seems to be something hanging pretty low on the tree of opportunity. Why spent months struggling with complex admin dashboard layouts and web frameworks when you could wire the underlying CRUD methods directly into LLM prompt callbacks? You could hypothetically make the LLM the exclusive interface for managing your next SaaS product. There are ways to make this just as robust and secure as an old school form punching application.
补充补充了几篇相关论文：多智能体扩展研究、智能体危害性基准等。
相关论文：《More Agents is all you need》(arxiv 2402.05120)。我没找到 AI 相关的「Agents considered harmful」，但有《AgentHarm：衡量 LLM 智能体危害性的基准》(arxiv 2410.09024)。另外那个「Agents considered harmful」不是 AI 相关的。
TaurenHunter查看英文原文
"More Agents is all you need" https://arxiv.org/abs/2402.05120 I could not find a "Agents considered harmful" related to AI, but there is this one: "AgentHarm: A benchmark for measuring harmfulness of LLM agents" https://arxiv.org/pdf/2410.09024 This "Agents considered harmful" is not AI-related: https://www.scribd.com/document/361564026/Math-works-09
相关资源
从这篇论文所有 HN 讨论帖的全部评论里整理出来的链接。
历次讨论
- 2025Hacker News 讨论帖207 分 · 156 评
同领域还值得读
DeepSeek-R1：通过强化学习激励 LLM 的推理能力
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via RL
研究如何用强化学习激励大语言模型的推理能力，提出 DeepSeek-R1，并探讨 RL 训练对模型推理表现的影响。
AI 与机器学习2025 · 1,351 分 · 1,056 评 · 引用 30进阶 · 约 80 分钟编辑精选1-bit LLM 时代：面向低成本计算的三值参数
The Era of 1-bit LLMs: ternary parameters for cost-effective computing
提出用三值参数 {-1, 0, 1} 替代 LLM 中的浮点权重，即所谓“1-bit LLM”。
AI 与机器学习2024 · 1,040 分 · 447 评 · 引用 19进阶 · 约 45 分钟编辑精选DeepSeek-V3.2：推进开放大语言模型的前沿
DeepSeek-v3.2: Pushing the frontier of open large language models
这是 DeepSeek-V3.2 的技术报告，延续了 DeepSeek 开源权重模型的路线，目标是让开放模型继续逼近甚至追平前沿闭源模型。
AI 与机器学习2025 · 982 分 · 465 评进阶 · 约 90 分钟编辑精选通过自我对弈与通用强化学习掌握国际象棋和将棋（AlphaZero）
Mastering Chess and Shogi by Self-Play with General Reinforcement Learning
DeepMind 的 AlphaZero 论文：用通用强化学习算法（自我博弈 + MCTS + 神经网络），从零开始仅数小时训练便在国际象棋和将棋上击败了世界顶级引擎 Stock…
AI 与机器学习2017 · 539 分 · 270 评 · 引用 13进阶 · 约 90 分钟编辑精选用强化学习发现更快的矩阵乘法算法
Discovering faster matrix multiplication algorithms with reinforcement learning
论文提出 AlphaTensor，用强化学习搜索矩阵乘法算法。
AI 与机器学习2022 · 518 分 · 111 评专业 · 约 90 分钟编辑精选