{"id":2628,"date":"2024-05-18T14:45:17","date_gmt":"2024-05-18T06:45:17","guid":{"rendered":"https:\/\/infernews.com\/?p=2628"},"modified":"2024-05-18T15:11:13","modified_gmt":"2024-05-18T07:11:13","slug":"ai-agent-%e6%9c%89%e4%bb%80%e9%ba%bc%e7%94%a8%ef%bc%9f","status":"publish","type":"post","link":"https:\/\/infernews.com\/blog\/ai-agent-%e6%9c%89%e4%bb%80%e9%ba%bc%e7%94%a8%ef%bc%9f\/","title":{"rendered":"AI Agent \u6709\u4ec0\u9ebc\u7528\uff1f"},"content":{"rendered":"\n<p>A.I. \u4e0d\u65b7\u666e\u53ca\uff0c\u53ef\u80fd\u8d8a\u569f\u8d8a\u591a\u6280\u8853\u540d\u7a31\u4ee4\u4eba\u83ab\u660e\u8cbb\u89e3\u3002\u9019\u5169\u689d\u5f71\u7247\u53ef\u80fd\u6703\u4ee4\u4f60\u66f4\u5fb9\u5e95\u4e86\u89e3 A.I. \u662f\u5982\u4f55\u904b\u4f5c\u3002<\/p>\n\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"AI Agents! Giving Reasoning and Tools to LLMs - Context &amp;amp; Code Examples\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_GZWFLEj0UqI\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FGZWFLEj0UqI%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/GZWFLEj0UqI\" \/><meta itemprop=\"duration\" content=\"PT35M4S\" \/><meta itemprop=\"uploadDate\" content=\"2024-04-05T17:46:35Z\" \/><\/div><div id=\"lyte_GZWFLEj0UqI\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FGZWFLEj0UqI%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">AI Agents! Giving Reasoning and Tools to LLMs - Context &amp; Code Examples<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/GZWFLEj0UqI\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FGZWFLEj0UqI%2F0.jpg\" alt=\"AI Agents! Giving Reasoning and Tools to LLMs - Context &amp;amp; Code Examples\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"Artificial Intelligence Agents! The new trend in AI and language model innovation, giving LLMs the ability to reason through problems, call external functions\/api, use tools to attack a problem, and even automatically managing other agents themselves. This video is broken into two parts, a high level overview of what it means to refer to an application as an Agent, and the second being a comprehensive deep dive into my own example, an supervisor architecture with a central manager agent that controls a social media analysis subagent, and a report writing subagent. Additional Resources - Github: https:\/\/github.com\/ALucek\/ai-agents-video\/ @LangChain LangGraph Tutorial Series: https:\/\/www.youtube.com\/playlist?list=PLfaIDFEXuae16n2TWUkKq5PgJ0w6Pkwtg OpenAI Function Calling: https:\/\/platform.openai.com\/docs\/guides\/function-calling OpenAI Tools: https:\/\/platform.openai.com\/docs\/assistants\/tools LangChain Agents Documentation: https:\/\/python.langchain.com\/docs\/modules\/agents\/ LangGraph Documentation: https:\/\/python.langchain.com\/docs\/langgraph LangSmith Trace From Example: https:\/\/smith.langchain.com\/public\/b6682759-8e00-494e-952a-1c29b069f6ed\/r Chapters: 00:00 - Part 1: Intro to Agents 02:06 - ReAct Paper 03:30 - ChatGPT Is An Agent 04:39 - Function Calling Overview 06:36 - Function Calling &amp; Tools 08:15 - Artistic Interpretation 10:26 - Part 2: Code Example 11:10 - Agent Supervisor Architecture 13:38 - Creating Custom Tools 16:37 - Defining Agents 19:03 - Supervisor Agent Creation 21:39 - Sub Agent Creation &amp; Graphing 23:54 - Graph Workflow Setup 24:28 - Defining Agent Edges 26:38 - Trying it out! 27:45 - Behind the Scenes with LangSmith 32:35 - Concluding Thoughts\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n\n<figure class=\"wp-block-embed-youtube wp-block-embed is-type-video is-provider-youtube wp-embed-aspect-16-9 wp-has-aspect-ratio\"><div class=\"lyte-wrapper\" title=\"Breaking Down &amp;amp; Testing FIVE LLM Agent Architectures - (Reflexion, LATs, P&amp;amp;E, ReWOO, LLMCompiler)\" style=\"width:853px;max-width:100%;margin:5px auto;\"><div class=\"lyMe\" id=\"WYL_ZJlfF1ESXVw\" itemprop=\"video\" itemscope itemtype=\"https:\/\/schema.org\/VideoObject\"><div><meta itemprop=\"thumbnailUrl\" content=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FZJlfF1ESXVw%2Fhqdefault.jpg\" \/><meta itemprop=\"embedURL\" content=\"https:\/\/www.youtube.com\/embed\/ZJlfF1ESXVw\" \/><meta itemprop=\"duration\" content=\"PT36M39S\" \/><meta itemprop=\"uploadDate\" content=\"2024-04-30T20:18:03Z\" \/><\/div><div id=\"lyte_ZJlfF1ESXVw\" data-src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FZJlfF1ESXVw%2Fhqdefault.jpg\" class=\"pL\"><div class=\"tC\"><div class=\"tT\" itemprop=\"name\">Breaking Down &amp; Testing FIVE LLM Agent Architectures - (Reflexion, LATs, P&amp;E, ReWOO, LLMCompiler)<\/div><\/div><div class=\"play\"><\/div><div class=\"ctrl\"><div class=\"Lctrl\"><\/div><div class=\"Rctrl\"><\/div><\/div><\/div><noscript><a href=\"https:\/\/youtu.be\/ZJlfF1ESXVw\" rel=\"nofollow\"><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/infernews.com\/blog\/wp-content\/plugins\/wp-youtube-lyte\/lyteCache.php?origThumbUrl=https%3A%2F%2Fi.ytimg.com%2Fvi%2FZJlfF1ESXVw%2F0.jpg\" alt=\"Breaking Down &amp;amp; Testing FIVE LLM Agent Architectures - (Reflexion, LATs, P&amp;amp;E, ReWOO, LLMCompiler)\" width=\"853\" height=\"460\" \/><br \/>Watch this video on YouTube<\/a><\/noscript><meta itemprop=\"description\" content=\"Large Language Model Agents have taken over LLM and Artificial Intelligence application design by storm, so this time we check out and simplify six main concepts and five popular papers documenting ways to set up language model based agents, as well as directly testing examples. Resources - @LangChain Agent Tutorials &amp; Code - https:\/\/www.youtube.com\/playlist?list=PLfaIDFEXuae16n2TWUkKq5PgJ0w6Pkwtg Overview on LLM Agents - https:\/\/youtu.be\/GZWFLEj0UqI Link to Miro Board PDF: https:\/\/drive.google.com\/file\/d\/1ESnrIy4c5LPOhNHRnn87Cv7DU_i0-_J9\/view?usp=sharing Papers: Reflexion Paper: https:\/\/arxiv.org\/abs\/2303.11366 LATs Paper: https:\/\/arxiv.org\/abs\/2310.04406 Plan-And-Execute Paper: https:\/\/arxiv.org\/abs\/2305.04091 ReWOO Paper: https:\/\/arxiv.org\/abs\/2305.18323 LLMCompiler Paper: https:\/\/arxiv.org\/abs\/2312.04511 LangSmith Traces: Basic Reflection: https:\/\/smith.langchain.com\/public\/604a986b-a751-48ed-9dda-738bd2780ea5\/r Reflexion: https:\/\/smith.langchain.com\/public\/83b0f3a3-b788-471b-ae1b-57167ceef37c\/r LATs: https:\/\/smith.langchain.com\/public\/d4541960-3f1a-4e53-9ec7-d223736f64b7\/r Plan-And-Execute: https:\/\/smith.langchain.com\/public\/c13392c5-e058-4bbe-b25e-aac7214a28df\/r ReWOO: https:\/\/smith.langchain.com\/public\/ee636208-6914-4c97-9d29-64c572c6ecc0\/r LLMCompiler: https:\/\/smith.langchain.com\/public\/28857a8a-b9b1-45d5-8403-ded9f95fab6d\/r Chapters: 00:00 - Intro 01:08 - Basic Reflection 02:44 - Basic Reflection Testing 06:32 - Reflexion Actor 09:57 - Reflexion Action Testing 12:25 - Language Agent Tree Search (LATs) 17:04 - LATs Testing 20:54 - Plan And Execute 23:38 - Plan And Execute Testing 26:28 - Reasoning Without Observation (ReWOO) 29:26 - ReWOO Testing 31:11 - LLMCompiler 35:19 - LLMCompiler Testing 36:05 - Outro\"><\/div><\/div><div class=\"lL\" style=\"max-width:100%;width:853px;margin:5px auto;\"><\/div><figcaption><\/figcaption><\/figure>\n\n\n<p><\/p>\n","protected":false},"excerpt":{"rendered":"<p>A.I. \u4e0d\u65b7\u666e\u53ca\uff0c\u53ef\u80fd\u8d8a\u569f\u8d8a\u591a\u6280\u8853\u540d\u7a31\u4ee4\u4eba\u83ab\u660e\u8cbb\u89e3\u3002\u9019\u5169\u689d\u5f71\u7247\u53ef\u80fd\u6703\u4ee4\u4f60\u66f4\u5fb9\u5e95\u4e86\u89e3 A.I. \u662f\u5982\u4f55\u904b\u4f5c\u3002<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"googlesitekit_rrm_CAowvqSiDA:productID":"","footnotes":""},"categories":[27],"tags":[],"class_list":["post-2628","post","type-post","status-publish","format-standard","hentry","category-paper"],"_links":{"self":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/2628","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/comments?post=2628"}],"version-history":[{"count":0,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/posts\/2628\/revisions"}],"wp:attachment":[{"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/media?parent=2628"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/categories?post=2628"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/infernews.com\/blog\/wp-json\/wp\/v2\/tags?post=2628"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}