2 papers
cs.LG2025
AbideGym: Turning Static RL Worlds into Adaptive Challenges
Abi Aryan, Zac Liu, Aaron Childress
Agents trained with reinforcement learning often develop brittle policies that fail when dynamics shift, a problem amplified by static benchmarks. AbideGym, a dynamic MiniGrid wrap…
cs.LG2025
Causal Reflection with Language Models
Abi Aryan, Zac Liu
While LLMs exhibit impressive fluency and factual recall, they struggle with robust causal reasoning, often relying on spurious correlations and brittle patterns. Similarly, tradit…