4 papers
Agents in the Wild: Where Research Meets Deployment
Grace Hui Yang, Pranav N. Venkit, Hooman Sedghamiz +3
Agentic systems large language model (LLM) based architectures capable of reasoning, planning, acting, and coordinating with tools and other agents are rapidly transitioning from r…
Magentic-UI: Towards Human-in-the-loop Agentic Systems
Hussein Mozannar, Gagan Bansal, Cheng Tan +17
AI agents powered by large language models are increasingly capable of autonomously completing complex, multi-step tasks using external tools. Yet, they still fall short of human-l…
Interactive Debugging and Steering of Multi-Agent AI Systems
Will Epperson, Gagan Bansal, Victor Dibia +4
Fully autonomous teams of LLM-powered AI agents are emerging that collaborate to perform complex tasks for users. What challenges do developers face when trying to build and debug…
Concept Distillation from Strong to Weak Models via Hypotheses-to-Theories Prompting
Emmanuel Aboah Boateng, Cassiano O. Becker, Nabiha Asghar +5
Hand-crafting high quality prompts to optimize the performance of language models is a complicated and labor-intensive process. Furthermore, when migrating to newer, smaller, or we…