2 papers
cs.AI2026
When Does Feedback Help? Auditing Learned Voltage-Clamp Experimental Design
Rayan Nyaupane, Abhiram Bhupatiraju
A learned scientific controller can outperform a misspecified planner without benefiting from feedback. We audit two synthetic voltage-clamp tasks with a training-selected fixed pr…
cs.AI2026
Are Stated Reasoning Steps Causally Load-Bearing?
Abhiram Bhupatiraju, Rayan Nyaupane
Chain-of-thought (CoT) monitoring assumes that the reasoning a model writes reflects the computation that directly produces its answer. Previous faithfulness metrics have been pred…