activity
20242026
collaborators

5 papers

cs.AI2026

AI Learning and Conceptual Transfer in the Game of Hidden Rules

Christo Mathew, Wentian Wang, Jacob Feldman +4

This report summarizes the work conducted on the Game of Hidden Rules (GOHR), focusing on reinforcement learning agents trained to infer hidden rules from trial-and-error feedback,…

cs.LG2026

Interpretable GOHR Agents via Sparse Autoencoders

Shiwei Tan, Yusong Zhao, Weiyi Qin +6

A central challenge in interpreting learned decision-making systems is to determine whether their internal representations contain concepts that help explain their behavior. We rep…

physics.soc-ph2026

The mechanistic origin of branching-driven nucleation in abrupt phase transitions

Leyang Xue, Shengling Gao, Bnaya Gross +5

Phase transitions are the macroscopic manifestation of microscopic processes that drive a system towards a new state. The detailed evolution of these processes, particularly in abr…

cs.LG2025

Toward a Metrology for Artificial Intelligence: Hidden-Rule Environments and Reinforcement Learning

Christo Mathew, Wentian Wang, Jacob Feldman +4

We investigate reinforcement learning in the Game Of Hidden Rules (GOHR) environment, a complex puzzle in which an agent must infer and execute hidden rules to clear a 66 b…

cs.CL2024

MMLU-SR: A Benchmark for Stress-Testing Reasoning Capability of Large Language Models

Wentian Wang, Sarthak Jain, Paul Kantor +3

We propose MMLU-SR, a novel dataset designed to measure the true comprehension abilities of Large Language Models (LLMs) by challenging their performance in question-answering task…