5 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…
Leveraging Speech to Identify Signatures of Insight and Transfer in Problem Solving
Linas Nasvytis, Judith E. Fan
Many problems seem to require a flash of insight to solve. What form do these sudden insights take, and what impact do they have on how people approach similar problems in the futu…
Rethinking Out-of-Distribution Detection for Reinforcement Learning: Advancing Methods for Evaluation and Detection
Linas Nasvytis, Kai Sandbrink, Jakob Foerster +2
While reinforcement learning (RL) algorithms have been successfully applied across numerous sequential decision-making problems, their generalization to unforeseen testing environm…
Trust and Time Preference: Measuring a Causal Effect in a Random-Assignment Experiment
Linas Nasvytis
Large amounts of evidence suggest that trust levels in a country are an important determinant of its macroeconomic growth. In this paper, we investigate one channel through which t…