6 papers
auto-psych: Automating the science of mind using agent-driven theory discovery and experimentation
Ben Prystawski, Kushin Mukherjee, Daniel Wurgaft +4
AI-based scientific automation is increasingly possible by using agents to generate hypotheses, design experiments, and analyze data. Data collection is a major bottleneck in this…
CORE: Contrastive Reflection Enables Rapid Improvements in Reasoning
Linas Nasvytis, Simon Jerome Han, Ben Prystawski +3
Language models can use verifiable rewards to improve at a wide variety of reasoning tasks. However, both parametric (e.g. RLVR) and non-parametric (e.g. prompt optimization) appro…
Language and Experience: A Computational Model of Social Learning in Complex Tasks
Cédric Colas, Tracey Mills, Ben Prystawski +4
The ability to combine linguistic guidance from others with direct experience is central to human development, enabling safe and rapid learning in new environments. How do people i…
Lossy communication constrains iterated learning
Ben Prystawski, Dilip Arumugam, Noah D. Goodman
Humans' distinctive role in the world can largely be attributed to our capacity for iterated learning, a process by which knowledge is expanded and refined over generations. A rang…
Context informs pragmatic interpretation in vision-language models
Alvin Wei Ming Tan, Ben Prystawski, Veronica Boyce +1
Iterated reference games - in which players repeatedly pick out novel referents using language - present a test case for agents' ability to perform context-sensitive pragmatic reas…
Scaling up the think-aloud method
Daniel Wurgaft, Ben Prystawski, Kanishk Gandhi +3
The think-aloud method, where participants voice their thoughts as they solve a task, is a valuable source of rich data about human reasoning processes. Yet, it has declined in pop…