[Theory] TODAY: 3/14 Talks at TTIC: Shuyan Zhou, Carnegie Mellon University
Mary Marre
mmarre at ttic.edu
Thu Mar 14 10:17:45 CDT 2024
*When:* Thursday, March 14, 2024 at* 11:00** a**m CT *
*Where: *Talk will be given *live, in-person* at
TTIC, 6045 S. Kenwood Avenue
5th Floor, Room 530
*Virtually:* *via *Panopto (*livestream
<https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=d9a754e1-4d1f-4d31-ace8-b12c01622b72>*
)
* *limited access: see info below*
*Who: * Shuyan Zhou, Carnegie Mellon University
------------------------------
*Title: *Solving Real-World Tasks with AI Agents
*Abstract: *For years, my dream has been to create autonomous AI agents
capable of carrying out tedious procedural tasks (e.g., arranging
conference travel), allowing me to focus on more creative and exciting
tasks. Modern AI models, especially large language models (LLMs) like
ChatGPT, have suddenly brought us much closer to achieving such AI agents.
But, has my dream already come true? In this talk, I will answer this
question by delving into my systematic evaluation of AI agents in realistic
tasks. The evaluation uncovers many critical limitations of AI agents, such
as tool use, abstract reasoning, and knowledge cutoff. It suggests that
LLMs are crucial yet early steps towards AI autonomy. To address these
challenges, I will introduce my research of a more suitable “language” for
AIs, which overcomes the inherent limitations of using natural language for
task solving. Then, I will discuss my work on teaching AI agents to learn
new tools by reading the tool documentation rather than direct
demonstrations. Finally, I will discuss my future plans for comprehensive
AI agent evaluations, agent foundations, and the application of AI agents
to critical sectors in the real world.
*Bio: *Shuyan Zhou is a final-year PhD student at the Language Technologies
Institute at CMU, advised by Graham Neubig. Her research in NLP and AI
focuses on creating AI agents for real-world tasks, such as using computers
and generating code. Her work has been recognized at top natural language
processing and machine learning conferences and journals such as ICLR,
ICML, ACL, EMNLP, and TACL. You can find more about her at
https://shuyanzhou.com
*Host: **Matthew Walter* <mwalter at ttic.edu>
*Access to this livestream is limited to TTIC / UChicago (press panopto
link and sign in to your UChicago account with CNetID).
Mary C. Marre
Faculty Administrative Support
*Toyota Technological Institute*
*6045 S. Kenwood Avenue, Rm 517*
*Chicago, IL 60637*
*773-834-1757*
*mmarre at ttic.edu <mmarre at ttic.edu>*
On Wed, Mar 13, 2024 at 12:41 PM Mary Marre <mmarre at ttic.edu> wrote:
> *When:* Thursday, March 14, 2024 at* 11:00** a**m CT *
>
>
> *Where: *Talk will be given *live, in-person* at
>
> TTIC, 6045 S. Kenwood Avenue
>
> 5th Floor, Room 530
>
>
> *Virtually:* *via *Panopto (*livestream
> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=d9a754e1-4d1f-4d31-ace8-b12c01622b72>*
> )
>
> * *limited access: see info below*
>
>
>
> *Who: * Shuyan Zhou, Carnegie Mellon University
>
>
> ------------------------------
> *Title: *Solving Real-World Tasks with AI Agents
>
> *Abstract: *For years, my dream has been to create autonomous AI agents
> capable of carrying out tedious procedural tasks (e.g., arranging
> conference travel), allowing me to focus on more creative and exciting
> tasks. Modern AI models, especially large language models (LLMs) like
> ChatGPT, have suddenly brought us much closer to achieving such AI agents.
> But, has my dream already come true? In this talk, I will answer this
> question by delving into my systematic evaluation of AI agents in realistic
> tasks. The evaluation uncovers many critical limitations of AI agents, such
> as tool use, abstract reasoning, and knowledge cutoff. It suggests that
> LLMs are crucial yet early steps towards AI autonomy. To address these
> challenges, I will introduce my research of a more suitable “language” for
> AIs, which overcomes the inherent limitations of using natural language for
> task solving. Then, I will discuss my work on teaching AI agents to learn
> new tools by reading the tool documentation rather than direct
> demonstrations. Finally, I will discuss my future plans for comprehensive
> AI agent evaluations, agent foundations, and the application of AI agents
> to critical sectors in the real world.
>
> *Bio: *Shuyan Zhou is a final-year PhD student at the Language
> Technologies Institute at CMU, advised by Graham Neubig. Her research in
> NLP and AI focuses on creating AI agents for real-world tasks, such as
> using computers and generating code. Her work has been recognized at top
> natural language processing and machine learning conferences and journals
> such as ICLR, ICML, ACL, EMNLP, and TACL. You can find more about her at
> https://shuyanzhou.com
>
> *Host: **Matthew Walter* <mwalter at ttic.edu>
>
> *Access to this livestream is limited to TTIC / UChicago (press panopto
> link and sign in to your UChicago account with CNetID).
>
>
>
>
>
> Mary C. Marre
> Faculty Administrative Support
> *Toyota Technological Institute*
> *6045 S. Kenwood Avenue, Rm 517*
> *Chicago, IL 60637*
> *773-834-1757*
> *mmarre at ttic.edu <mmarre at ttic.edu>*
>
>
> On Thu, Mar 7, 2024 at 4:43 PM Mary Marre <mmarre at ttic.edu> wrote:
>
>> *When:* Thursday, March 14, 2024 at* 11:00** a**m CT *
>>
>>
>> *Where: *Talk will be given *live, in-person* at
>>
>> TTIC, 6045 S. Kenwood Avenue
>>
>> 5th Floor, Room 530
>>
>>
>> *Virtually:* *via *Panopto (*livestream
>> <https://uchicago.hosted.panopto.com/Panopto/Pages/Viewer.aspx?id=d9a754e1-4d1f-4d31-ace8-b12c01622b72>*
>> )
>>
>> * *limited access: see info below*
>>
>>
>>
>> *Who: * Shuyan Zhou, Carnegie Mellon University
>>
>>
>> ------------------------------
>> *Title: *Solving Real-World Tasks with AI Agents
>>
>> *Abstract: *For years, my dream has been to create autonomous AI agents
>> capable of carrying out tedious procedural tasks (e.g., arranging
>> conference travel), allowing me to focus on more creative and exciting
>> tasks. Modern AI models, especially large language models (LLMs) like
>> ChatGPT, have suddenly brought us much closer to achieving such AI agents.
>> But, has my dream already come true? In this talk, I will answer this
>> question by delving into my systematic evaluation of AI agents in realistic
>> tasks. The evaluation uncovers many critical limitations of AI agents, such
>> as tool use, abstract reasoning, and knowledge cutoff. It suggests that
>> LLMs are crucial yet early steps towards AI autonomy. To address these
>> challenges, I will introduce my research of a more suitable “language” for
>> AIs, which overcomes the inherent limitations of using natural language for
>> task solving. Then, I will discuss my work on teaching AI agents to learn
>> new tools by reading the tool documentation rather than direct
>> demonstrations. Finally, I will discuss my future plans for comprehensive
>> AI agent evaluations, agent foundations, and the application of AI agents
>> to critical sectors in the real world.
>>
>> *Bio: *Shuyan Zhou is a final-year PhD student at the Language
>> Technologies Institute at CMU, advised by Graham Neubig. Her research in
>> NLP and AI focuses on creating AI agents for real-world tasks, such as
>> using computers and generating code. Her work has been recognized at top
>> natural language processing and machine learning conferences and journals
>> such as ICLR, ICML, ACL, EMNLP, and TACL. You can find more about her at
>> https://shuyanzhou.com
>>
>> *Host: **Matthew Walter* <mwalter at ttic.edu>
>>
>> *Access to this livestream is limited to TTIC / UChicago (press panopto
>> link and sign in to your UChicago account with CNetID).
>>
>>
>>
>>
>> Mary C. Marre
>> Faculty Administrative Support
>> *Toyota Technological Institute*
>> *6045 S. Kenwood Avenue, Rm 517*
>> *Chicago, IL 60637*
>> *773-834-1757*
>> *mmarre at ttic.edu <mmarre at ttic.edu>*
>>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.cs.uchicago.edu/pipermail/theory/attachments/20240314/47e571ce/attachment-0001.html>
More information about the Theory
mailing list