Auto-Mates @IJCAI23

Thank you all for participating in the workshop!!! The presentations can be found here

Workshop agenda

08:45 - 09:00 Gathering
09:00 - 09:10 Opening remarks
09:10 - 10:00 Opening keynote talk: Workshop Chairs. Harnessing AI to automate work:
10:00 - 10:30 Invited talk - Mind2Web: Towards a Generalist Agent for the Web
10:30 - 11:00 Coffee break
11:00 - 11:20 Paper 1 - Semantic Parsing for Complex Data Retrieval: Targeting Query Plans vs. SQL for No-Code Access to Relational Databases
11:20 - 11:40 Paper 2 - Accelerating Chatbot Design: Leveraging Large Language Models for Enhanced Efficiency
11:40 - 12:20 Keynote: Dr. Martin Hirzel. Title: Low-Code Programming Models
12:30 - 14:00 Lunch break
14:00 - 15:30 Paper session

Paper 3 - Semantic UI Understanding in the Era of AI
Paper 4 - AI-Driven Automation for "Classical" MDP
Paper 5 - Enhancing Trust in LLM-Based AI Automation Agents: New Considerations and Future Challenges

15:30 - 16:00 Coffee break
16:00 - 16:40 Keynote: Prof. Shen Jiasi. Title: Automating Software Development: Challenges and Solutions
16:40 - 16:50 Announcement of the Resiliency of Intelligent Automation Systems Challenge winners. Link
16:50 - 17:20 Roundtable - the future of NoCode Digital Automation (4-5 teams)
17:20 - 17:30 Conclusion
Social event

Register to the Workshop Here

Keynote

Martin Hirzel

http://hirzels.com/martin/

Traditionally, computer programming has been the prerogative of professional developers using textual programming languages such as C, Java, or Python. Low-code programming promises an alternative: letting citizen developers create programs using visual abstractions, demonstrations, or natural language. This talk begins by reviewing low-code literature from various research fields, explaining how techniques work while providing a unified point of view. Next, this talk provides a deep-dive into low-code for automating digital labor, especially for invoking APIs and for specifying APIs in a way that makes them easier to invoke. Low-code can help more people leverage recent advances in foundation models to become more productive and less dependent on scarce professional software developers.

Shen Jiasi

Software now plays a central role in numerous aspects of human society. Current software development practices involve significant developer effort in all phases of the software life cycle, including the development of new software, detection, and elimination of defects and security vulnerabilities in existing software, maintenance of legacy software, and integration of existing software into more contexts, with the quality of the resulting software still leaving much to be desired. This talk provides a general overview of how programming languages research addresses these challenges and discusses how AI research can help.

The First International Workshop on the Future of No-Code Digital Apprentices

No-code digital apprentices are a category of assistants that end-users, who lack programming expertise, can effectively teach, supervise and validate. These assistants are capable of making decisions, taking actions with a certain level of autonomy and identify when they are insufficiently trained and seek guidance from the human supervisor in such cases. They rely on a combination of advanced technologies, including natural language processing (NLP), conversational AI, robotic process automation, digital process automation, and business rules to function effectively.

In recent years, AI has made significant strides in various domains, including transformers, large language models, general AI, multi-modal representations, and generative models such as ChatGPT, Codex, HumAIns, Adept, and Auto-GPT. These advancements are poised to transform the field of digital assistants as they are becoming increasingly intelligent, autonomous, and better able to comprehend human work.

This workshop aims to unite researchers from different fields, such as programming languages, natural language processing, computer vision, knowledge representation, planning, human-computer interaction, and business process management. The primary objective is to establish a cross-disciplinary research agenda that will direct future work in the field of no-code digital apprentices and the AI-driven revolution in this area. By bringing together experts with diverse backgrounds, this workshop seeks to advance our understanding of the challenges and opportunities associated with NCDA and to encourage collaboration and innovation across disciplines.

We invite scientists, practitioners, and students from both academia and industry who share a passion for the potential ways in which AI can revolutionize the no-code automation field to participate in and submit their original work to this workshop. We encourage contributions that not only enhance NCDA with AI algorithms but also utilize their combination to address broader AI challenges. Moreover, we aim to attract individuals from research-oriented industrial divisions, such as Microsoft Research, Google Research, IBM Research, Adept.ai, and intelligence automation vendors like UiPath and Automation Anywhere. The workshop seeks to foster an open and collaborative atmosphere for exploring cutting-edge research and discussing innovative ideas in the field.

* You might also find the Resiliency of Intelligent Automation Systems Challenge interesting. Link
* A list of IJCAI23 workshops can be found at ijcai-23-workshops

-->

Program Chairs

Dr. Segev Shlomov

AI research scientist @ IBM Research Segev.Shlomov1@ibm.com

Mr. Avi Yaeli

Research scientist @ IBM Research aviy@il.ibm.com

Full Prof. Ronen Brafman

Ben-Gurion University, Israel brafman@bgu.ac.il

Prof. Xinyu Wang

University of Michigan, USA. xwangsd@umich.edu

Dr. Chenglong Wang

Microsoft Research. Redmond, USA chenglong.wang@microsoft.com

Program Commitee

Rotem Dror - University of Pennsylvania
Jose Cambronero - Microsoft
Nadia Polikarpova - University of California San Diego
Eran Yahav - Technion
Rui Dong - University of Michigan
Xinyun Chen - Google
Sergey Zeltyn - IBM Research
Yan Chen - University of Toronto
Yanju Chen - University of California, Santa Barbara
Lior Limonad - IBM Research
Jiani Huang - University of Pennsylvania
Kobi Gal - Ben-Gurion University