Log inSign up
Image
user avatar
Gagan Bansal
@bansalg_
Researching multi-agent stuff and human-agent interaction @msftresearch @ms_aifrontiers | Co-built AutoGen | Previously @uwcse, @iitdelhi
Seattle, WA
gagb.github.io
Joined November 2012
566
Following
3,040
Followers
  • Pinned
    user avatar
    Gagan Bansal
    @bansalg_
    May 1
    📢 Networks of agents are the future and in order to make them useful at scale, they must remain secure. So, we deployed an internal platform where every agent was always-on, had a known human "principal" (MS employee) that it reported to, and could interact w/ other agents via
    Image
    Image
    Image
    Image
    Image
    00:20
    user avatar
    Microsoft Research
    Microsoft
    @MSFTResearch
    Apr 30
    Safe agents don’t guarantee a safe ecosystem of interconnected agents. Microsoft Research examines what breaks when AI agents interact and why network-level risks require new approaches. Learn more: microsoft.com/en-us/research…
    1.6K
  • user avatar
    Gagan Bansal
    @bansalg_
    Dec 3, 2024
    ☀️Excited to share our new paper! Generative AI agents are powerful but complex—how do we design them for transparency and human control? 🤖✨ At the heart of this challenge is establishing common ground, a concept from human communication. Our new paper identifies 12 key
    Image
    85K
  • user avatar
    Gagan Bansal
    @bansalg_
    Oct 31, 2022
    Looking for research internships on #AI + #HCI?? Our team, Human-AI eXperiences (HAX) at @MSFTResearch, is hiring multiple interns for summer 2023 on topics related to human-centered AI (see 👇). cc: @SaleemaAmershi @vykthur @adamfourney Apply at aka.ms/haxinternships
    Join our growing team next year to pursue topics of interest including (but not limited to): Understanding, evaluating, and testing human-AI teams. Improving human interaction with AI (e.g., with large language models). For example, through human-centered innovations to ML models, training, and evaluation procedures (e.g., metrics), user interfaces, user training procedures, etc. Prototyping, simulating, and testing AI systems with humans-in-the-loop. Novel theories for human-AI interaction, e.g., defining and establishing appropriate levels of human trust and reliance on AI systems. Novel applications of AI (e.g., LLMs) for augmenting human performance. Novel mechanisms for improving human-AI interaction, e.g., by enabling meaningful human oversight, control of, and collaboration with AI systems. Developing interactive tools for responsible data collection, model building, and analyses of AI or LLMs. Studying and addressing technical or sociotechnical issues related to the cre
  • user avatar
    Gagan Bansal
    @bansalg_
    Jun 29, 2020
    New work on explainable AI! arxiv.org/abs/2006.14779 w/ @tongshuangwu, J. Zhu, R. Fok, @besanushi, @ecekamar, M. Ribeiro, and @dsweld. When AIs advise people, does an explanation of its reasoning actually help the person? Does it let the human outperform the AI? Does it ...(1/6)
  • user avatar
    Gagan Bansal
    @bansalg_
    Nov 29, 2023
    📢📢We are also hiring summer interns!📢📢 Come work with our teams in MSR AI Frontiers to conduct research on interaction between AI agents and people! jobs.careers.microsoft.com/global/en/job/…
    86K
  • user avatar
    Gagan Bansal
    @bansalg_
    Dec 18, 2023
    Our team will start reviewing internship applications on Jan 5th 2024! So please apply and submit material before that!
    user avatar
    Gagan Bansal
    @bansalg_
    Nov 29, 2023
    📢📢We are also hiring summer interns!📢📢 Come work with our teams in MSR AI Frontiers to conduct research on interaction between AI agents and people! jobs.careers.microsoft.com/global/en/job/…
    52K
  • user avatar
    Gagan Bansal
    @bansalg_
    Dec 14, 2021
    🚨Announcing #CHI2022 workshop on Trust and Reliance in AI-Human Teams (TRAIT) ft. keynote by @jdlee888, panel w/ #HCI & #AI experts, group activities & more! w/ @alison_m_smith, @ZanaBucinca, @tongshuangwu, @d19fe8, @JessicaHullman, @DrSimoneStumpf See: chi-trait.github.io
    As people increasingly interact w/ AI, it's important they understand when to appropriately trust or rely on AI outputs. But, What does trust & reliance mean in different human-AI teaming contexts? How do we measure trust and reliance? How do we shape appropriate trust and reliance?
  • user avatar
    Gagan Bansal
    @bansalg_
    Apr 30, 2022
    About 60 researchers brainstorming how to define, measure, and shape trust and reliance in human-AI interaction at the #TRAIT2022 hybrid workshop at #CHI2022 @sigchi
    Image
    Image
  • user avatar
    Gagan Bansal
    @bansalg_
    Jan 13, 2023
    🚨 Working on #AI + #HCI? Join the 2nd #CHI2023 workshop on Trust & Reliance in AI-Human Teams (TRAIT), focused on real-world human-AI use cases. Keynote: @Carryveggies & Michael Terry. w/ @alison_m_smith @ZanaBucinca @tongshuangwu @d19fe8 @JessicaHullman @DrSimoneStumpf
    Image
    14K
  • user avatar
    Gagan Bansal
    @bansalg_
    May 4, 2020
    Excited to share a draft of our new work on human-centered AI! arxiv.org/pdf/2004.13102… w/ @besanushi @ecekamar @erichorvitz @dsweld When an AI assists human decision-makers, e.g, by recommending its predictions, is the most accurate AI necessarily the best team-mate? (1/5)
    Image
  • user avatar
    Gagan Bansal
    @bansalg_
    Apr 30, 2022
    And its a wrap! We had 80 ppl/8 timezones join in a hybrid setting. Thanks to my co-organizers, speakers, pc, & participants for making this workshop possible @alison_m_smith @ZanaBucinca @tongshuangwu @d19fe8 @JessicaHullman @DrSimoneStumpf #TRAIT2022 #CHI2022
    Image
  • user avatar
    Gagan Bansal
    @bansalg_
    May 20, 2024
    CHI is one of my favorite conferences to attend! Here is a smol photo dump from fun moments with many many fantastic colleagues at #CHI2024 in Honolulu, Hawaii!
    Image
    Image
    Image
    Image
    5.2K
  • user avatar
    Gagan Bansal
    @bansalg_
    Apr 27, 2022
    Excited to be at #CHI2022 in-person!! DM me if you'd like to catch up there! We can talk about human-AI interaction (or not)!
  • user avatar
    Gagan Bansal
    @bansalg_
    Sep 5, 2024
    Excited to share pre-print on AutoGen Studio! 🤖🤖🤖 "We present #AutoGen Studio, a no-code developer tool for rapidly prototyping, debugging, and evaluating multi-agent workflows built upon the AutoGen framework." Paper: arxiv.org/abs/2408.15247 Code: github.com/microsoft/auto…
    Image
    6.8K