collaborators

7 papers

cs.AI2026

ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?

Jiajun Li, Mingshu Cai, Yixuan Li +5

Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR…

cs.LG2026

StarOR: Synergizing Tree Search and Test-Time Reinforcement Learning for Optimization Modeling

Jiajun Li, Yu Ding, Shisi Guan +2

Optimization modeling is inherently hierarchical, requiring a precise sequence of symbolic commitments. Traditional learning-based automated optimization modeling methods improve m…

cs.RO2026

Grasp-Then-Plan with Failure Attribution: A Closed Two-Stage Framework for Precise and Generalizable Robotic Manipulation

Jiahao Xu, Peiyuan Wang, Hanzhuo Zhang +7

In robotic manipulation, the tight coupling between grasping and motion planning often obscures the true source of failure, leading to inefficient trial-and-error. To enable effici…

cs.AI2026

MIND-Skill: Quality-Guaranteed Skill Generation via Multi-Agent Induction and Deduction

Yixuan Li, Mingshu Cai, Ziyang Xiao +3

Large language model (LLM) powered AI agents have emerged as a promising paradigm for autonomous problem-solving, yet they continue to struggle with complex, multi-step real-world…

cs.LG2026

Constraint Matters: Multi-Modal Representation for Reducing Mixed-Integer Linear programming

Jiajun Li, Yixuan Li, Ran Hou +8

Model reduction, which aims to learn a simpler model of the original mixed integer linear programming (MILP), can solve large-scale MILP problems much faster. Most existing model r…

cs.SE2026

MicLog: Towards Accurate and Efficient LLM-based Log Parsing via Progressive Meta In-Context Learning

Jianbo Yu, Yixuan Li, Hai Xu +5

Log parsing converts semi-structured logs into structured templates, forming a critical foundation for downstream analysis. Traditional syntax and semantic-based parsers often stru…