5 papers
Subagents vs Agent Skills: Executing Reusable Knowledge for Long-Horizon Agentic Tasks
Wasu Top Piriyakulkij, Rachel Lawrence, Alicia Curth +2
How can language model agents effectively leverage libraries of reusable knowledge to solve long-horizon tasks? Recent work has increasingly focused on agent skills: reusable capab…
Induction and Inquiry via Probabilistic Reasoning over Language and Code
Wasu Top Piriyakulkij, Sam Acquaviva, Cassidy Langenfeld +2
How humans grow and maintain abstract knowledge from the sparse, streaming noisy data of experience is a longstanding challenge in cognitive science. Any computational account must…
Playing ZendoWorld: Challenging AI Agents on Active Visual Concept Induction
Sophia Koehler, Antonia Wüst, Inga Ibs +5
A central challenge in building intelligent systems is enabling agents to jointly perceive complex inputs, form hypotheses about hidden patterns, and design informative experiments…
Learning Mental Models From Unreliable Evidence
Jeffrey Qin, Wasu Top Piriyakulkij, Zhuangfei Gao +4
Children expertly construct mental models under uncertainty despite limited world knowledge. Which computational principles make this possible? We study this question in an interac…
Joint Learning of Hierarchical Neural Options and Abstract World Model
Wasu Top Piriyakulkij, Wolfgang Lehrach, Kevin Ellis +1
Building agents that can perform new skills by composing existing skills is a long-standing goal of AI agent research. Towards this end, we investigate how to efficiently acquire a…