4 papers
Cross-Epoch Adaptive Rollout Optimization for RL Post-Training
Yiming Zong, Yige Wang, Jiashuo Jiang
LLM post-training often relies on reinforcement learning methods that sample multiple rollouts per prompt, yet most existing approaches use a fixed rollout budget for every prompt,…
Online Semi-infinite Linear Programming: Efficient Algorithms via Function Approximation
Yiming Zong, Jiashuo Jiang
We consider the dynamic resource allocation problem where the decision space is finite-dimensional, yet the solution must satisfy a large or even infinite number of constraints rev…
Adaptive Resolving Methods for Reinforcement Learning with Function Approximations
Jiashuo Jiang, Yiming Zong, Yinyu Ye
Reinforcement learning (RL) problems are fundamental in online decision-making and have been instrumental in finding an optimal policy for Markov decision processes (MDPs). Functio…
ML-Bench: Evaluating Large Language Models and Agents for Machine Learning Tasks on Repository-Level Code
Xiangru Tang, Yuliang Liu, Zefan Cai +21
Despite Large Language Models (LLMs) like GPT-4 achieving impressive results in function-level code generation, they struggle with repository-scale code understanding (e.g., coming…