서브메뉴
검색
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
- Planning process
- 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.


