大语言模型加持下的自动化引擎 | 自动化智能体系统

 

　　Resources:

 

　　1. Internet access for searches and information gathering.

 

　　2. Long Term memory management.

 

　　3. GPT-3.5 powered Agents for delegation of simple tasks.

 

　　4. File output.

 

　　Performance Evaluation:

 

　　1. Continuously review and analyze your actions to ensure you are performing to the best of your abilities.

 

　　2. Constructively self-criticize your big-picture behavior constantly.

 

　　3. Reflect on past decisions and strategies to refine your approach.

 

　　4. Every command has a cost, so be smart and efficient. Aim to complete tasks in the least number of steps.

 

　　You should only respond in JSON format as described below

 

　　Response Format:

 

　　{

 

　　"thoughts": {

 

　　"text": "thought",

 

　　"reasoning": "reasoning",

 

　　"plan": "- short bulleted\n- list that conveys\n- long-term plan",

 

　　"criticism": "constructive self-criticism",

 

　　"speak": "thoughts summary to say to user"

 

　　},

 

　　"command": {

 

　　"name": "command name",

 

　　"args": {

 

　　"arg name": "value"

 

　　}

 

　　}

 

　　}

 

　　Ensure the response can be parsed by Python json.loads

 

　　GPT-Engineer是另一个工程，它以自然语言描述的任务作为输入，创建一个完整的代码仓库。GPT-Engineer被指示考虑一些待构建的小组件列表，并在必要的时候要求用户澄清其问题。

 

　　下面是一个GPT-Engineer所使用的用于任务澄清的对话样本，该样本会发送给OpenAI ChatCompletion 终端。用户输入被包含在{{user input text}}格式中。

 

　　[

 

　　{

 

　　"role": "system",

 

　　"content": "You will read instructions and not carry them out, only seek to clarify them.\nSpecifically you will first summarise a list of super short bullets of areas that need clarification.\nThen you will pick one clarifying question, and wait for an answer from the user.\n"

 

　　},

 

　　{

 

　　"role": "user",

 

　　"content": "We are writing {{a Super Mario game in python. MVC components split in separate files. Keyboard control.}}\n"

 

　　},

 

　　{

 

　　"role": "assistant",

 

　　"content": "Summary of areas that need clarification:\n1. Specifics of the Super Mario game (e.g. level design, characters, gameplay mechanics)\n2. Details about the MVC components (e.g. which components are in each file)\n3. Keyboard control implementation (e.g. which keys to use, how to handle input)\n\nClarifying question:\nCan you provide more details about the Super Mario game, such as level design, characters, and gameplay mechanics?"

 

　　},

 

　　{

 

　　"role": "user",

 

　　"content": "{{There are 10 levels in total. The main character is a plumber named Mario, who can walk and jump. It is a classical platform game just like Super Mario. The main character moves from left to right, trying to get to the destination, where there are many obstacles and attacks from enemies in the process.}}\n\nIs anything else unclear? If yes, only answer in the form:\n{remaining unclear areas} remaining questions.\n{Next question}\nIf everything is sufficiently clear, only answer \"Nothing more to clarify.\"."

 

　　},

 

　　{

 

　　"role": "assistant",

 

　　"content": "Remaining unclear areas: 2 remaining questions.\nCan you provide more information about how the MVC components are split into separate files?"

 

　　},

 

　　{

 

　　"role": "user",

 

　　"content": "{{Make your own assumptions and state them explicitly before starting}}"

 

　　}

 

　　]

 

　　在这些澄清之后，智能体使用一个不同的系统消息来切换到代码编辑模式。系统提示消息为：

 

　　You will get instructions for code to write. You will write a very long answer. Make sure that every detail of the architecture is, in the end, implemented as code. Make sure that every detail of the architecture is, in the end, implemented as code.

 

　　Think step by step and reason yourself to the right decisions to make sure we get it right. You will first lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.

 

　　Then you will output the content of each file including ALL code. Each file must strictly follow a markdown code block format, where the following tokens must be replaced such that FILENAME is the lowercase file name including the file extension, LANG is the markup code block language for the code’s language, and CODE is the code:

 

　　FILENAME

 

　　```

 

　　CODE

 

　　```

 

　　You will start with the “entrypoint” file, then go to the ones that are imported by that file, and so on. Please note that the code should be fully functional. No placeholders.

 

　　Follow a language and framework appropriate best practice file naming convention. Make sure that files contain all imports, types etc. Make sure that code in different files are compatible with each other. Ensure to implement all code, if you are unsure, write a plausible implementation. Include module dependency or package manager dependency definition file. Before you finish, double check that all parts of the architecture is present in the files.

 

　　Useful to know: You almost always put different classes in different files. For Python, you always create an appropriate requirements.txt file. For NodeJS, you always create an appropriate package.json file. You always add a comment briefly describing the purpose of the function definition. You try to add comments explaining very complex bits of logic. You always follow the best practices for the requested languages in terms of describing the code written as a defined package/project.

 

　　Python toolbelt preferences:

 

　　- pytest

 

　　- dataclasses

 

　　对话举例：

 

　　[

 

　　{

 

　　"role": "system",

 

　　"content": "You will get instructions for code to write.\nYou will write a very long answer. Make sure that every detail of the architecture is, in the end, implemented as code.\nMake sure that every detail of the architecture is, in the end, implemented as code.\n\nThink step by step and reason yourself to the right decisions to make sure we get it right.\nYou will first lay out the names of the core classes, functions, methods that will be necessary, as well as a quick comment on their purpose.\n\nThen you will output the content of each file including ALL code.\nEach file must strictly follow a markdown code block format, where the following tokens must be replaced such that\nFILENAME is the lowercase file name including the file extension,\nLANG is the markup code block language for the code's language, and CODE is the code:\n\nFILENAME\n```LANG\nCODE\n```\n\nYou will start with the \"entrypoint\" file, then go to the ones that are imported by that file, and so on.\nPlease note that the code should be fully functional. No placeholders.\n\nFollow a language and framework appropriate best practice file naming convention.\nMake sure that files contain all imports, types etc. Make sure that code in different files are compatible with each other.\nEnsure to implement all code, if you are unsure, write a plausible implementation.\nInclude module dependency or package manager dependency definition file.\nBefore you finish, double check that all parts of the architecture is present in the files.\n\nUseful to know:\nYou almost always put different classes in different files.\nFor Python, you always create an appropriate requirements.txt file.\nFor NodeJS, you always create an appropriate package.json file.\nYou always add a comment briefly describing the purpose of the function definition.\nYou try to add comments explaining very complex bits of logic.\nYou always follow the best practices for the requested languages in terms of describing the code written as a defined\npackage/project.\n\n\nPython toolbelt preferences:\n- pytest\n- dataclasses\n"

 

　　},

 

　　#  … same conversation as earlier, ended with "Make your own assumptions and state them explicitly before starting".

 

　　{

 

　　"role": "assistant",

 

　　"content": "Assumptions:\n1. Model: The model will contain the game's data, such as level information, character states, and enemy positions.\n2. View: The view will handle the game's visuals, including rendering the game objects, backgrounds, and updating the display.\n3. Controller: The controller will manage user input, such as keyboard controls, and update the model accordingly.\n\nWith these assumptions in mind, is there any specific aspect of the keyboard control implementation you would like me to clarify?"

 

　　},

 

　　{

 

　　"role": "user",

 

　　"content": "Please now remember the steps:\n\nThink step by step and reason yourself to the right decisions to make sure we get it right.\nFirst lay out the names of the core classes, functions, methods that will be necessary, As well as a quick comment on their purpose.\n\nThen you will output the content of each file including ALL code.\nEach file must strictly follow a markdown code block format, where the following tokens must be replaced such that\nFILENAME is the lowercase file name including the file extension,\nLANG is the markup code block language for the code's language, and CODE is the code:\n\nFILENAME\n```LANG\nCODE\n```\n\nPlease note that the code should be fully functional. No placeholders.\n\nYou will start with the \"entrypoint\" file, then go to the ones that are imported by that file, and so on.\nFollow a language and framework appropriate best practice file naming convention.\nMake sure that files contain all imports, types etc. The code should be fully functional. Make sure that code in different files are compatible with each other.\nBefore you finish, double check that all parts of the architecture is present in the files.\n"

 

　　}

 

　　]

 

　　挑战

 

　　在对构建以LLM为中心的智能体的核心思想以及应用示范过了一遍之后，我发现一些局限性：

 

　　有限的上下文长度：上下文容量的局限会限制可以包含的历史信息、细节指令、API调用上下文以及响应。系统的设计必须考虑工作在此通信带宽限制之上。如果有更长的或者无限的上下文窗口，类似从过去错误中学习的自我反思之类的机制就可以收获更大。虽然向量数据的存取与检索可以提供一个更大的知识池，它们的表示能力还是无法和全注意力机制相提并论

 

　　长期规划与任务分解中的挑战：在一段跨度很长的历史信息上进行规划以及解决方案空间的高效探索都是非常具有挑战性的。LLMs在面对异常错误的时候很难对规划进行调整，这与从试错中学习的人类相比还是远不够看

 

　　自然语言接口的可靠性：当前的智能系统还依赖于自然语言作为LLMs与外部组件（如记忆与工具）的接口。然而，模型输出的可靠性还是一个问题。LLMs可能会犯格式化错误，并且偶尔也会犯病（比如拒绝遵循指令）。结果，大量的智能体示例都在重点关注如何转换模型的输出

 

　　引用

 

　　引用格式：

 

　　“

 

　　Weng, Lilian. (Jun 2023). LLM-powered Autonomous Agents". Lil’Log. https://lilianweng.github.io/posts/2023-06-23-agent/.

 

　　”

 

　　或者

 

　　@article{weng2023prompt,

 

　　title   = "LLM-powered Autonomous Agents"",

 

　　author  = "Weng, Lilian",

 

　　journal = "lilianweng.github.io",

 

　　year    = "2023",

 

　　month   = "Jun",

 

　　url     = "https://lilianweng.github.io/posts/2023-06-23-agent/"

 

　　}