3 papers
cs.AI2026
Inducing Reasoning Primitives from Agent Traces
Zhihan Lei, Jiarui Yan, Joshua Momo +1
ReAct-style LLM agents often rediscover the same reasoning routines across problems, yet leave those routines trapped in transient scratchpads. We introduce Reasoning Primitive Ind…
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.CV2025
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…