5 papers
When Context Changes: Understanding Update Failures in LLMs
Junyu Guo, Yuchen Fang, Shangding Gu +3
As preferences, goals, and facts change, LLM agents must use the current state while earlier versions remain in context. Yet they can answer with an old value of the same variable,…
LLMs Should Express Uncertainty Explicitly
Junyu Guo, Shangding Gu, Ming Jin +2
Large language models (LLMs) often produce confident yet incorrect answers, which can lead to risky failures in real-world applications. We study whether post-training can make a m…
StyleBench: Evaluating thinking styles in Large Language Models
Junyu Guo, Shangding Gu, Ming Jin +2
Structured reasoning can improve the inference performance of large language models (LLMs), but it also introduces computational cost and control constraints. When additional reaso…
Don't Trade Off Safety: Diffusion Regularization for Constrained Offline RL
Junyu Guo, Zhi Zheng, Donghao Ying +4
Constrained reinforcement learning (RL) seeks high-performance policies under safety constraints. We focus on an offline setting where the agent has only a fixed dataset -- common…
Reinforcement Learning for SBM Graphon Games with Re-Sampling
Peihan Huo, Oscar Peralta, Junyu Guo +2
The Mean-Field approximation is a tractable approach for studying large population dynamics. However, its assumption on homogeneity and universal connections among all agents limit…