6 papers
Resolving Action Bottleneck: Agentic Reinforcement Learning Informed by Token-Level Energy
Langzhou He, Junyou Zhu, Yue Zhou +7
Agentic reinforcement learning trains large language models using multi-turn trajectories that interleave long reasoning traces with short environment-facing actions. Common policy…
When Users Change Their Mind: Evaluating Interruptible Agents in Long-Horizon Web Navigation
Henry Peng Zou, Chunyu Miao, Wei-Chieh Huang +16
As LLM agents transition from short, static problem solving to executing complex, long-horizon tasks in dynamic environments, the ability to handle user interruptions, such as addi…
Actor-Curator: Co-adaptive Curriculum Learning via Policy-Improvement Bandits for RL Post-Training
Zhengyao Gu, Jonathan Light, Raul Astudillo +7
Post-training large foundation models with reinforcement learning typically relies on massive and heterogeneous datasets, making effective curriculum learning both critical and cha…
RECODE-H: A Benchmark for Research Code Development with Interactive Human Feedback
Chunyu Miao, Henry Peng Zou, Yangning Li +28
Large language models (LLMs) show the promise in supporting scientific research implementation, yet their ability to generate correct and executable code remains limited. Existing…
TestNUC: Enhancing Test-Time Computing Approaches and Scaling through Neighboring Unlabeled Data Consistency
Henry Peng Zou, Zhengyao Gu, Yue Zhou +7
Test-time computing approaches, which leverage additional computational resources during inference, have been proven effective in enhancing large language model performance. This w…
Scaling Laws for Many-Shot In-Context Learning with Self-Generated Annotations
Zhengyao Gu, Henry Peng Zou, Yankai Chen +3
The high cost of obtaining high-quality annotated data for in-context learning (ICL) has motivated the development of methods that use self-generated annotations in place of ground…