极限套娃，Agent自动设计Agentic系统！ - 链载Ai

Agent智能体系统正在作为通用工具被广泛研究和应用，解决复杂问题通常需要由多个组件组成的复合智能体系统，而手工设计的解决方案最终会被学习到的更高效的解决方案所取代。

ADAS的定义和目标

ADAS的三个关键组成部分

自动化智能体系统设计（ADAS）的三个关键组成部分。搜索空间决定了ADAS中可以表示哪些Agent系统。搜索算法指定了ADAS方法如何探索搜索空间。评估函数定义了如何根据目标目标（如性能）评估候选Agent。

通过在编码、科学和数学等多个领域的广泛实验，展示了该算法能够逐步发明具有新颖设计的智能体，这些智能体的性能ingFang SC", "Hiragino Sans GB", "Microsoft YaHei UI", "Microsoft YaHei", Arial, sans-serif;font-size: 16px;letter-spacing: 0.544px;text-indent: 0em;">大大超过了手工设计的最先进智能体。

元智能体搜索在ARC挑战上的结果。(a) 元智能体搜索基于不断增长的先前发现的存档，逐步发现高性能智能体。通过五次评估智能体，在保留的测试集上报告中位数准确度和95%的自举置信区间。(b) 元智能体搜索在ARC挑战上发现的最佳智能体的可视化。

来自ARC挑战的一个示例任务。给定输入-输出网格示例，人工智能系统被要求学习转换规则，然后将这些学到的规则应用于测试网格，以预测最终答案。

Meta Agent Search与多个领域内最先进的手工设计智能体之间的性能比较。Meta Agent Search在每个领域中发现的智能体都优于基线。报告了在保留的测试集上的测试准确度和95%自举置信区间。每个领域的搜索是独立进行的。

将MGSM中的顶级智能体转移到其他数学领域时的性能。元智能体搜索发现的智能体在不同数学领域中始终优于基线。我们报告了测试准确度和95%自举置信区间。顶级智能体的名称由元智能体搜索生成。

使用以下提示来指导元智能体基于先前发现的智能体存档来设计新智能体。

Youareanexpertmachinelearningresearchertestingvariousagenticsystems.Yourobjectiveistodesignbuildingblockssuchaspromptsandcontrolflowswithinthesesystemstosolvecomplextasks.Youraimistodesignanoptimalagentperformingwellon[BriefDescriptionoftheDomain].[FrameworkCode][OutputInstructionsandExamples][DiscoveredAgentArchive](initializedwithbaselines,updatedateveryiteration)#YourtaskYouaredeeplyfamiliarwithpromptingtechniquesandtheagentworksfromtheliterature.Yourgoalistomaximizethespecifiedperformancemetricsbyproposinginterestinglynewagents.Observethediscoveredagentscarefullyandthinkaboutwhatinsights,lessons,orsteppingstonescanbelearnedfromthem.Becreativewhenthinkingaboutthenextinterestingagenttotry.Youareencouragedtodrawinspirationfromrelatedagentpapersoracademicpapersfromotherresearchareas.Usetheknowledgefromthearchiveandinspirationfromacademicliteraturetoproposethenextinterestingagenticsystemdesign.THINKOUTSIDETHEBOX.

#OutputInstructionandExample:Thefirstkeyshouldbe(“thought”),anditshouldcaptureyourthoughtprocessfordesigningthenextfunction.Inthe“thought”section,firstreasonaboutwhatthenextinterestingagenttotryshouldbe,thendescribeyourreasoningandtheoverallconceptbehindtheagentdesign,andfinallydetailtheimplementationsteps.Thesecondkey(“name”)correspondstothenameofyournextagentarchitecture.Finally,thelastkey(“code”)correspondstotheexact“forward()”functioninPythoncodethatyouwouldliketotry.YoumustwriteCOMPLETECODEin“code”:Yourcodewillbepartoftheentireproject,sopleaseimplementcomplete,reliable,reusablecodesnippets.Hereisanexampleoftheoutputformatforthenextagent:{“thought”:“**Insights:**Yourinsightsonwhatshouldbethenextinterestingagent.**OverallIdea:**yourreasoningandtheoverallconceptbehindtheagentdesign.**Implementation:**describetheimplementationstepbystep.”,“name”:“Nameofyourproposedagent”,“code”:“defforward(self,taskInfo):#Yourcodehere”}##WRONGImplementationexamples:[Examplesofpotentialmistakesthemetaagentmaymakeinimplementation]

[GeneratedAgentfromPreviousIteration]Carefullyreviewtheproposednewarchitectureandreflectonthefollowingpoints:1.**Interestingness**:Assesswhetheryourproposedarchitectureisinterestingorinnovativecomparedtoexistingmethodsinthearchive.Ifyoudeterminethattheproposedarchitectureisnotinteresting,suggestanewarchitecturethataddressestheseshortcomings.-Makesuretocheckthedifferencebetweentheproposedarchitectureandpreviousattempts.-ComparetheproposalandthearchitecturesinthearchiveCAREFULLY,includingtheiractualdifferencesintheimplementation.-Decidewhetherthecurrentarchitectureisinnovative.-USECRITICALTHINKING!2.**ImplementationMistakes**:Identifyanymistakesyoumayhavemadeintheimplementation.Reviewthecodecarefully,debuganyissuesyoufind,andprovideacorrectedversion.REMEMBERchecking"##WRONGImplementationexamples"intheprompt.3.**Improvement**:Basedontheproposedarchitecture,suggestimprovementsinthedetailedimplementationthatcouldincreaseitsperformanceoreffectiveness.Inthisstep,focusonrefiningandoptimizingtheexistingimplementationwithoutalteringtheoveralldesignframework,exceptifyouwanttoproposeadifferentarchitectureifthecurrentisnotinteresting.-Observecarefullyaboutwhethertheimplementationisactuallydoingwhatitissupposedtodo.-Checkifthereisredundantcodeorunnecessarystepsintheimplementation.Replacethemwitheffectiveimplementation.-Trytoavoidtheimplementationbeingtoosimilartothepreviousagent.Andthen,youneedtoimproveorrevisetheimplementation,orimplementthenewproposedarchitecturebasedonthereflection.Yourresponseshouldbeorganizedasfollows:"reflection"rovideyourthoughtsontheinterestingnessofthearchitecture,identifyanymistakesintheimplementation,andsuggestimprovements."thought":Reviseyourpreviousproposalorproposeanewarchitectureifnecessary,usingthesameformatastheexampleresponse."name"rovideanamefortherevisedornewarchitecture.(Don’tputwordslike"new"or"improved"inthename.)"code"rovidethecorrectedcodeoranimprovedimplementation.Makesureyouactuallyimplementyourfixandimprovementinthiscode.

当在执行生成的代码期间遇到错误时，会进行反思并重新运行代码。如果错误持续存在，这个过程会重复进行，最多五次。以下是用于自我反思任何运行时错误的提示：