5 papers
GraphBU: MILP Instance Generation with Graph-Native Block Units
Xiaolei Guo, Chenyu Zhou, Jianghao Lin +1
Mixed-integer linear programming (MILP) instances used for solver development are hard to obtain when models come from private or application-specific pipelines. A generator must k…
OSDN: Improving Delta Rule with Provable Online Preconditioning in Linear Attention
Chenyu Zhou, Hongpei Li, Yuerou Liu +3
Linear attention and state-space models offer constant-memory alternatives to softmax attention, but often struggle with in-context associative recall. The Delta Rule mitigates thi…
Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering
Chenyu Zhou, Huacan Chai, Wenteng Chen +18
Large language model (LLM) agents are increasingly built less by changing model weights than by reorganizing the runtime around them. Capabilities that earlier systems expected the…
Auto-Formulating Dynamic Programming Problems with Large Language Models
Chenyu Zhou, Jingyuan Yang, Linwei Xin +3
Dynamic programming (DP) is a fundamental method in operations research, but formulating DP models has traditionally required expert knowledge of both the problem context and DP te…
StepORLM: A Self-Evolving Framework With Generative Process Supervision For Operations Research Language Models
Chenyu Zhou, Tianyi Xu, Jianghao Lin +1
Large Language Models (LLMs) have shown promising capabilities for solving Operations Research (OR) problems. While reinforcement learning serves as a powerful paradigm for LLM tra…