AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation

AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Us...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-10
Main Authors: Wu, Qingyun, Bansal, Gagan, Zhang, Jieyu, Wu, Yiran, Li, Beibin, Zhu, Erkang, Jiang, Li, Zhang, Xiaoyun, Zhang, Shaokun, Liu, Jiale, Ahmed Hassan Awadallah, White, Ryen W, Burger, Doug, Wang, Chi
Format: Article
Language:English
Subjects:
Decision making
Multiagent systems
Operations research
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page
container_issue
container_start_page
container_title arXiv.org
container_volume
creator Wu, Qingyun
Bansal, Gagan
Zhang, Jieyu
Wu, Yiran
Li, Beibin
Zhu, Erkang
Jiang, Li
Zhang, Xiaoyun
Zhang, Shaokun
Liu, Jiale
Ahmed Hassan Awadallah
White, Ryen W
Burger, Doug
Wang, Chi
description AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.
format article
fullrecord <record><control><sourceid>proquest</sourceid><recordid>TN_cdi_proquest_journals_2852160586</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><sourcerecordid>2852160586</sourcerecordid><originalsourceid>FETCH-proquest_journals_28521605863</originalsourceid><addsrcrecordid>eNqNikELgjAYQEcQJOV_GHQezK0t6SZiedBO3WXFksn4Zm6Tfn4S_YBOD957K5QwzjOSHxjboNT7gVLK5JEJwRNUFzG4i4YTrkDdrYEeX_U7kEXhpmlxMY7WPFQwDjyejcJttMGQotcQcOlg1pP_1h1aP5X1Ov1xi_bn6lbWZJzcK2ofusHFCZbUsVywTFKRS_7f9QG4tjsk</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>2852160586</pqid></control><display><type>article</type><title>AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation</title><source>Publicly Available Content (ProQuest)</source><creator>Wu, Qingyun ; Bansal, Gagan ; Zhang, Jieyu ; Wu, Yiran ; Li, Beibin ; Zhu, Erkang ; Jiang, Li ; Zhang, Xiaoyun ; Zhang, Shaokun ; Liu, Jiale ; Ahmed Hassan Awadallah ; White, Ryen W ; Burger, Doug ; Wang, Chi</creator><creatorcontrib>Wu, Qingyun ; Bansal, Gagan ; Zhang, Jieyu ; Wu, Yiran ; Li, Beibin ; Zhu, Erkang ; Jiang, Li ; Zhang, Xiaoyun ; Zhang, Shaokun ; Liu, Jiale ; Ahmed Hassan Awadallah ; White, Ryen W ; Burger, Doug ; Wang, Chi</creatorcontrib><description>AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.</description><identifier>EISSN: 2331-8422</identifier><language>eng</language><publisher>Ithaca: Cornell University Library, arXiv.org</publisher><subject>Decision making ; Multiagent systems ; Operations research</subject><ispartof>arXiv.org, 2023-10</ispartof><rights>2023. This work is published under http://creativecommons.org/licenses/by/4.0/ (the “License”). Notwithstanding the ProQuest Terms and Conditions, you may use this content in accordance with the terms of the License.</rights><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://www.proquest.com/docview/2852160586?pq-origsite=primo$$EHTML$$P50$$Gproquest$$Hfree_for_read</linktohtml><link.rule.ids>780,784,25744,37003,44581</link.rule.ids></links><search><creatorcontrib>Wu, Qingyun</creatorcontrib><creatorcontrib>Bansal, Gagan</creatorcontrib><creatorcontrib>Zhang, Jieyu</creatorcontrib><creatorcontrib>Wu, Yiran</creatorcontrib><creatorcontrib>Li, Beibin</creatorcontrib><creatorcontrib>Zhu, Erkang</creatorcontrib><creatorcontrib>Jiang, Li</creatorcontrib><creatorcontrib>Zhang, Xiaoyun</creatorcontrib><creatorcontrib>Zhang, Shaokun</creatorcontrib><creatorcontrib>Liu, Jiale</creatorcontrib><creatorcontrib>Ahmed Hassan Awadallah</creatorcontrib><creatorcontrib>White, Ryen W</creatorcontrib><creatorcontrib>Burger, Doug</creatorcontrib><creatorcontrib>Wang, Chi</creatorcontrib><title>AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation</title><title>arXiv.org</title><description>AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.</description><subject>Decision making</subject><subject>Multiagent systems</subject><subject>Operations research</subject><issn>2331-8422</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2023</creationdate><recordtype>article</recordtype><sourceid>PIMPY</sourceid><recordid>eNqNikELgjAYQEcQJOV_GHQezK0t6SZiedBO3WXFksn4Zm6Tfn4S_YBOD957K5QwzjOSHxjboNT7gVLK5JEJwRNUFzG4i4YTrkDdrYEeX_U7kEXhpmlxMY7WPFQwDjyejcJttMGQotcQcOlg1pP_1h1aP5X1Ov1xi_bn6lbWZJzcK2ofusHFCZbUsVywTFKRS_7f9QG4tjsk</recordid><startdate>20231003</startdate><enddate>20231003</enddate><creator>Wu, Qingyun</creator><creator>Bansal, Gagan</creator><creator>Zhang, Jieyu</creator><creator>Wu, Yiran</creator><creator>Li, Beibin</creator><creator>Zhu, Erkang</creator><creator>Jiang, Li</creator><creator>Zhang, Xiaoyun</creator><creator>Zhang, Shaokun</creator><creator>Liu, Jiale</creator><creator>Ahmed Hassan Awadallah</creator><creator>White, Ryen W</creator><creator>Burger, Doug</creator><creator>Wang, Chi</creator><general>Cornell University Library, arXiv.org</general><scope>8FE</scope><scope>8FG</scope><scope>ABJCF</scope><scope>ABUWG</scope><scope>AFKRA</scope><scope>AZQEC</scope><scope>BENPR</scope><scope>BGLVJ</scope><scope>CCPQU</scope><scope>DWQXO</scope><scope>HCIFZ</scope><scope>L6V</scope><scope>M7S</scope><scope>PIMPY</scope><scope>PQEST</scope><scope>PQQKQ</scope><scope>PQUKI</scope><scope>PRINS</scope><scope>PTHSS</scope></search><sort><creationdate>20231003</creationdate><title>AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation</title><author>Wu, Qingyun ; Bansal, Gagan ; Zhang, Jieyu ; Wu, Yiran ; Li, Beibin ; Zhu, Erkang ; Jiang, Li ; Zhang, Xiaoyun ; Zhang, Shaokun ; Liu, Jiale ; Ahmed Hassan Awadallah ; White, Ryen W ; Burger, Doug ; Wang, Chi</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-proquest_journals_28521605863</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2023</creationdate><topic>Decision making</topic><topic>Multiagent systems</topic><topic>Operations research</topic><toplevel>online_resources</toplevel><creatorcontrib>Wu, Qingyun</creatorcontrib><creatorcontrib>Bansal, Gagan</creatorcontrib><creatorcontrib>Zhang, Jieyu</creatorcontrib><creatorcontrib>Wu, Yiran</creatorcontrib><creatorcontrib>Li, Beibin</creatorcontrib><creatorcontrib>Zhu, Erkang</creatorcontrib><creatorcontrib>Jiang, Li</creatorcontrib><creatorcontrib>Zhang, Xiaoyun</creatorcontrib><creatorcontrib>Zhang, Shaokun</creatorcontrib><creatorcontrib>Liu, Jiale</creatorcontrib><creatorcontrib>Ahmed Hassan Awadallah</creatorcontrib><creatorcontrib>White, Ryen W</creatorcontrib><creatorcontrib>Burger, Doug</creatorcontrib><creatorcontrib>Wang, Chi</creatorcontrib><collection>ProQuest SciTech Collection</collection><collection>ProQuest Technology Collection</collection><collection>Materials Science &amp; Engineering Collection</collection><collection>ProQuest Central (Alumni)</collection><collection>ProQuest Central</collection><collection>ProQuest Central Essentials</collection><collection>AUTh Library subscriptions: ProQuest Central</collection><collection>Technology Collection</collection><collection>ProQuest One Community College</collection><collection>ProQuest Central</collection><collection>SciTech Premium Collection</collection><collection>ProQuest Engineering Collection</collection><collection>Engineering Database</collection><collection>Publicly Available Content (ProQuest)</collection><collection>ProQuest One Academic Eastern Edition (DO NOT USE)</collection><collection>ProQuest One Academic</collection><collection>ProQuest One Academic UKI Edition</collection><collection>ProQuest Central China</collection><collection>Engineering Collection</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Wu, Qingyun</au><au>Bansal, Gagan</au><au>Zhang, Jieyu</au><au>Wu, Yiran</au><au>Li, Beibin</au><au>Zhu, Erkang</au><au>Jiang, Li</au><au>Zhang, Xiaoyun</au><au>Zhang, Shaokun</au><au>Liu, Jiale</au><au>Ahmed Hassan Awadallah</au><au>White, Ryen W</au><au>Burger, Doug</au><au>Wang, Chi</au><format>book</format><genre>document</genre><ristype>GEN</ristype><atitle>AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation</atitle><jtitle>arXiv.org</jtitle><date>2023-10-03</date><risdate>2023</risdate><eissn>2331-8422</eissn><abstract>AutoGen is an open-source framework that allows developers to build LLM applications via multiple agents that can converse with each other to accomplish tasks. AutoGen agents are customizable, conversable, and can operate in various modes that employ combinations of LLMs, human inputs, and tools. Using AutoGen, developers can also flexibly define agent interaction behaviors. Both natural language and computer code can be used to program flexible conversation patterns for different applications. AutoGen serves as a generic infrastructure to build diverse applications of various complexities and LLM capacities. Empirical studies demonstrate the effectiveness of the framework in many example applications, with domains ranging from mathematics, coding, question answering, operations research, online decision-making, entertainment, etc.</abstract><cop>Ithaca</cop><pub>Cornell University Library, arXiv.org</pub><oa>free_for_read</oa></addata></record>
fulltext fulltext
identifier EISSN: 2331-8422
ispartof arXiv.org, 2023-10
issn 2331-8422
language eng
recordid cdi_proquest_journals_2852160586
source Publicly Available Content (ProQuest)
subjects Decision making
Multiagent systems
Operations research
title AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-14T23%3A54%3A27IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=document&rft.atitle=AutoGen:%20Enabling%20Next-Gen%20LLM%20Applications%20via%20Multi-Agent%20Conversation&rft.jtitle=arXiv.org&rft.au=Wu,%20Qingyun&rft.date=2023-10-03&rft.eissn=2331-8422&rft_id=info:doi/&rft_dat=%3Cproquest%3E2852160586%3C/proquest%3E%3Cgrp_id%3Ecdi_FETCH-proquest_journals_28521605863%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=2852160586&rft_id=info:pmid/&rfr_iscdi=true