본문

서브메뉴

One Step Towards Autonomous AI Agent: Reasoning, Alignment and Planning
One Step Towards Autonomous AI Agent: Reasoning, Alignment and Planning
One Step Towards Autonomous AI Agent: Reasoning, Alignment and Planning

상세정보

자료유형  
 학위논문 서양
최종처리일시  
20250211152728
ISBN  
9798383677742
DDC  
004
저자명  
Chen, Xiusi.
서명/저자  
One Step Towards Autonomous AI Agent: Reasoning, Alignment and Planning
발행사항  
[Sl] : University of California, Los Angeles, 2024
발행사항  
Ann Arbor : ProQuest Dissertations & Theses, 2024
형태사항  
182 p
주기사항  
Source: Dissertations Abstracts International, Volume: 86-02, Section: B.
주기사항  
Advisor: Wang, Wei.
학위논문주기  
Thesis (Ph.D.)--University of California, Los Angeles, 2024.
초록/해제  
요약The recent development of artificial intelligence (AI) has facilitated the prosperity of foundation models, such as large language models (LLMs) and vision models. The foundation models have reshaped the way people interact with tools to improve productivity and creativity by taking over many use cases where people use conventional computer software. Being aware of the promising emerging abilities observed from the foundation models, a more interactive picture has been envisioned where the foundation models drive a group of AI agents that play different roles to fulfill more diverse and complex tasks, further benefiting human society. Like humans, AI agents should be able to reason and plan over complex tasks, and they should also be well aligned with human preferences and values. Advanced foundation models provide a solid foundation for the implementation of AI agents. However, agents based on the current foundation models have intrinsic limitations inherited from existing foundation models. In addition to hallucination, these foundation models can demonstrate biases presented in their training data, resulting in output that can be discriminatory. LLMs can expose sensitive or personal information embedded in their training data, risking user privacy and security. Finally, due to the generative nature of the prevailing foundation models, it is desirable to incorporate planning modules generatively, so the planning process can be seamlessly accomplished during the generation process. In summary, the gaps between the current state-of-the-art and the goals underscore the need for further efforts to improve the reasoning ability, the alignment of human values and the generative planning ability of the foundation models. My ultimate research goal is to build AI agents that are reliable, unbiased, and capable of planning so that they can be safely and effectively applied in various domains. To achieve this goal, I have divided my research into the following subtasks:1. Knowledge-Enhanced Reasoning that aims to improve the factual accuracy and logical coherence of LLM outputs by integrating external knowledge.2. Minimally Supervised Data Generation and Selection that aims to improve the efficiency of fine-tuning or in-context learning by selecting the most informative training data.3. Automatic Constitution Discovery and Self-alignment that aims to mitigate the risk of generating incorrect, nonsensical, biased or private information.4. Agents Planning that aims to enable multi-agent strategic learning by incorporating generative goal-guided planning.In this thesis, I will first emphasize the significance of building such reliable, unbiased, capable-of-planning AI agents, and then introduce four lines of my work, and finally the future challenges and opportunities.
일반주제명  
Computer science
일반주제명  
Computer engineering
키워드  
Diffusion model
키워드  
Foundation models
키워드  
Large language models
키워드  
Planning process
키워드  
Reasoning ability
기타저자  
University of California, Los Angeles Computer Science 0201
기본자료저록  
Dissertations Abstracts International. 86-02B.
전자적 위치 및 접속  
로그인 후 원문을 볼 수 있습니다.

MARC

 008250123s2024        us                              c    eng  d
■001000017163594
■00520250211152728
■006m          o    d                
■007cr#unu||||||||
■020    ▼a9798383677742
■035    ▼a(MiAaPQ)AAI31490529
■040    ▼aMiAaPQ▼cMiAaPQ
■0820  ▼a004
■1001  ▼aChen,  Xiusi.
■24510▼aOne  Step  Towards  Autonomous  AI  Agent:  Reasoning,  Alignment  and  Planning
■260    ▼a[Sl]▼bUniversity  of  California,  Los  Angeles▼c2024
■260  1▼aAnn  Arbor▼bProQuest  Dissertations  &  Theses▼c2024
■300    ▼a182  p
■500    ▼aSource:  Dissertations  Abstracts  International,  Volume:  86-02,  Section:  B.
■500    ▼aAdvisor:  Wang,  Wei.
■5021  ▼aThesis  (Ph.D.)--University  of  California,  Los  Angeles,  2024.
■520    ▼aThe  recent  development  of  artificial  intelligence  (AI)  has  facilitated  the  prosperity  of  foundation  models,  such  as  large  language  models  (LLMs)  and  vision  models.  The  foundation  models  have  reshaped  the  way  people  interact  with  tools  to  improve  productivity  and  creativity  by  taking  over  many  use  cases  where  people  use  conventional  computer  software.  Being  aware  of  the  promising  emerging  abilities  observed  from  the  foundation  models,  a  more  interactive  picture  has  been  envisioned  where  the  foundation  models  drive  a  group  of  AI  agents  that  play  different  roles  to  fulfill  more  diverse  and  complex  tasks,  further  benefiting  human  society.  Like  humans,  AI  agents  should  be  able  to  reason  and  plan  over  complex  tasks,  and  they  should  also  be  well  aligned  with  human  preferences  and  values.  Advanced  foundation  models  provide  a  solid  foundation  for  the  implementation  of  AI  agents.  However,  agents  based  on  the  current  foundation  models  have  intrinsic  limitations  inherited  from  existing  foundation  models.  In  addition  to  hallucination,  these  foundation  models  can  demonstrate  biases  presented  in  their  training  data,  resulting  in  output  that  can  be  discriminatory.  LLMs  can  expose  sensitive  or  personal  information  embedded  in  their  training  data,  risking  user  privacy  and  security.  Finally,  due  to  the  generative  nature  of  the  prevailing  foundation  models,  it  is  desirable  to  incorporate  planning  modules  generatively,  so  the  planning  process  can  be  seamlessly  accomplished  during  the  generation  process.  In  summary,  the  gaps  between  the  current  state-of-the-art  and  the  goals  underscore  the  need  for  further  efforts  to  improve  the  reasoning  ability,  the  alignment  of  human  values  and  the  generative  planning  ability  of  the  foundation  models.  My  ultimate  research  goal  is  to  build  AI  agents  that  are  reliable,  unbiased,  and  capable  of  planning  so  that  they  can  be  safely  and  effectively  applied  in  various  domains.  To  achieve  this  goal,  I  have  divided  my  research  into  the  following  subtasks:1.  Knowledge-Enhanced  Reasoning  that  aims  to  improve  the  factual  accuracy  and  logical  coherence  of  LLM  outputs  by  integrating  external  knowledge.2.  Minimally  Supervised  Data  Generation  and  Selection  that  aims  to  improve  the  efficiency  of  fine-tuning  or  in-context  learning  by  selecting  the  most  informative  training  data.3.  Automatic  Constitution  Discovery  and  Self-alignment  that  aims  to  mitigate  the  risk  of  generating  incorrect,  nonsensical,  biased  or  private  information.4.  Agents  Planning  that  aims  to  enable  multi-agent  strategic  learning  by  incorporating  generative  goal-guided  planning.In  this  thesis,  I  will  first  emphasize  the  significance  of  building  such  reliable,  unbiased,  capable-of-planning  AI  agents,  and  then  introduce  four  lines  of  my  work,  and  finally  the  future  challenges  and  opportunities.
■590    ▼aSchool  code:  0031.
■650  4▼aComputer  science
■650  4▼aComputer  engineering
■653    ▼aDiffusion  model
■653    ▼aFoundation  models
■653    ▼aLarge  language  models
■653    ▼aPlanning  process
■653    ▼aReasoning  ability
■690    ▼a0984
■690    ▼a0464
■690    ▼a0800
■71020▼aUniversity  of  California,  Los  Angeles▼bComputer  Science  0201.
■7730  ▼tDissertations  Abstracts  International▼g86-02B.
■790    ▼a0031
■791    ▼aPh.D.
■792    ▼a2024
■793    ▼aEnglish
■85640▼uhttp://www.riss.kr/pdu/ddodLink.do?id=T17163594▼nKERIS▼z이  자료의  원문은  한국교육학술정보원에서  제공합니다.

미리보기

내보내기

chatGPT토론

Ai 추천 관련 도서


    신착도서 더보기
    최근 3년간 통계입니다.

    소장정보

    • 예약
    • 소재불명신고
    • 나의폴더
    • 우선정리요청
    • 비도서대출신청
    • 야간 도서대출신청
    소장자료
    등록번호 청구기호 소장처 대출가능여부 대출정보
    TF12921 전자도서 대출가능 마이폴더 부재도서신고 비도서대출신청 야간 도서대출신청

    * 대출중인 자료에 한하여 예약이 가능합니다. 예약을 원하시면 예약버튼을 클릭하십시오.

    해당 도서를 다른 이용자가 함께 대출한 도서

    관련 인기도서

    로그인 후 이용 가능합니다.