1 code implementation • 3 Mar 2025 • Will Epperson, Gagan Bansal, Victor Dibia, Adam Fourney, Jack Gerrits, Erkang Zhu, Saleema Amershi
Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users.
no code implementations • 28 Nov 2024 • Gagan Bansal, Jennifer Wortman Vaughan, Saleema Amershi, Eric Horvitz, Adam Fourney, Hussein Mozannar, Victor Dibia, Daniel S. Weld
Remarkable advancements in modern generative foundation models have enabled the development of sophisticated and highly capable autonomous agents that can observe their environment, invoke tools, and communicate with other agents to solve problems.
no code implementations • 7 Nov 2024 • Adam Fourney, Gagan Bansal, Hussein Mozannar, Cheng Tan, Eduardo Salinas, Erkang, Zhu, Friederike Niedtner, Grace Proebsting, Griffin Bassman, Jack Gerrits, Jacob Alber, Peter Chang, Ricky Loynd, Robert West, Victor Dibia, Ahmed Awadallah, Ece Kamar, Rafah Hosn, Saleema Amershi
Magentic-One uses a multi-agent architecture where a lead agent, the Orchestrator, plans, tracks progress, and re-plans to recover from errors.
1 code implementation • 9 Aug 2024 • Victor Dibia, Jingya Chen, Gagan Bansal, Suff Syed, Adam Fourney, Erkang Zhu, Chi Wang, Saleema Amershi
Multi-agent systems, where multiple agents (generative AI models + tools) collaborate, are emerging as an effective pattern for solving long-running, complex tasks in numerous domains.
no code implementations • 7 Jun 2023 • John Joon Young Chung, Ece Kamar, Saleema Amershi
However, creating high-quality datasets with LLMs can be challenging.
no code implementations • 19 Apr 2023 • Charvi Rastogi, Marco Tulio Ribeiro, Nicholas King, Harsha Nori, Saleema Amershi
Through the design process we highlight the importance of sensemaking and human-AI communication to leverage complementary strengths of humans and generative models in collaborative auditing.
no code implementations • 29 Oct 2022 • Victor Dibia, Adam Fourney, Gagan Bansal, Forough Poursabzi-Sangdeh, Han Liu, Saleema Amershi
Large language models have demonstrated great potential to assist programmers in generating code.
no code implementations • 16 May 2022 • Maurice Jakesch, Zana Buçinca, Saleema Amershi, Alexandra Olteanu
Compared to the US-representative sample, AI practitioners appear to consider responsible AI values as less important and emphasize a different set of values.
1 code implementation • 5 May 2022 • Jessie J. Smith, Saleema Amershi, Solon Barocas, Hanna Wallach, Jennifer Wortman Vaughan
Transparency around limitations can improve the scientific rigor of research, help ensure appropriate interpretation of research findings, and make research claims more credible.
no code implementations • 21 Jul 2017 • Patrice Y. Simard, Saleema Amershi, David M. Chickering, Alicia Edelman Pelton, Soroush Ghorashi, Christopher Meek, Gonzalo Ramos, Jina Suh, Johan Verwey, Mo Wang, John Wernsing
This significantly limits the number of machine learning systems that can be created and has led to a mismatch between the demand for machine learning systems and the ability for organizations to build them.
no code implementations • NeurIPS 2016 • Tzu-Kuo Huang, Lihong Li, Ara Vartanian, Saleema Amershi, Jerry Zhu
We present a theoretical analysis of active learning with more realistic interactions with human oracles.
no code implementations • 16 Sep 2014 • Patrice Simard, David Chickering, Aparna Lakshmiratan, Denis Charles, Leon Bottou, Carlos Garcia Jurado Suarez, David Grangier, Saleema Amershi, Johan Verwey, Jina Suh
Based on the machine's output, the teacher can revise the definition of the task or make it more precise.