3 papers
cs.AI2026
Learning Reusable Agent Subroutines from Experience
Zhihan Lei, Jiarui Yan, Joshua Momo +1
Existing methods induce various forms of knowledge from agent traces, from sample workflows to programmatic skills. We propose ARISE (Agent Routine Induction from Successful Experi…
cs.LG2026
Learning to Construct Practical Agentic Systems
Aditya Kumar, Zhihan Lei, Jerry Yan +6
Automated design and optimization of agentic LLM-based systems leads to sophisticated systems that substantially improve result quality over off-the-shelf agentic patterns. However…
cs.CV2024
VLM Agents Generate Their Own Memories: Distilling Experience into Embodied Programs of Thought
Gabriel Sarch, Lawrence Jang, Michael J. Tarr +3
Large-scale generative language and vision-language models (LLMs and VLMs) excel in few-shot learning but require high-quality demonstrations. We propose In-Context Abstraction Lea…