Ziming Li 李梓铭

SWE-Trail: History-Guided Trajectory Collection for Coding Agent Training

Ziming Li, Lu Yu, Jiatan Huang, Qing Cui, Jun Zhou, Chuxu Zhang

arXiv preprint, 2026

paper

History-guided exploration for collecting training trajectories for coding agents, evaluated on SWE-bench.

Same Signal, Opposite Meaning: Direction-Informed Adaptive Learning for LLM Agents

Ziming Li, Jiatan Huang, Xiaoguang Guo, Guiling Wang, Chuxu Zhang

Neural Information Processing Systems (NeurIPS), 2026

paper code

The same uncertainty or difficulty signal can indicate opposite compute utility across environments and backbones. DIAL learns when additional test-time computation actually helps instead of assuming a fixed signal direction.

Graph is a Substrate Across Data Modalities

Ziming Li, Xiao-Ming Wu, Zehong Wang, Jiazheng Li, Yijun Tian, Jinhe Bi, Yunpu Ma, Yanfang Ye, Chuxu Zhang

International Conference on Machine Learning (ICML), 2026

paper code model dataset

Graph structure is treated as a persistent structural substrate shared across modalities and tasks rather than rebuilt per task. A unified structural schema and interleaved role-based training outperform task-isolated and naive multi-task baselines.

MDForge: Agentic Molecular Dynamics Pipeline Design under Sparse Simulator Feedback

Zehong Wang, Yijun Ma, Connor R. Schmidt, Tianyi Ma, Weixiang Sun, Ziming Li, Xiaoguang Guo, Chuxu Zhang, Matthew J. Webber, Yanfang Ye

Conference on Empirical Methods in Natural Language Processing (EMNLP), 2026

paper

An LLM agent designs molecular dynamics pipelines from verbal rewards produced by expert debate, matching human specialists on binding free-energy benchmarks and discovering an experimentally validated high-affinity binder.

RSM: Reinforced Subgraph Matching Framework with Fine-grained Operation based Search Plan

Ziming Li, Yuequn Dou, Youhuan Li, Xinhuan Chen, Chuxu Zhang

ACM International Conference on Web Search and Data Mining (WSDM), 2025

paper code

A new search framework for learned subgraph matching that uses reinforcement learning and GNNs to generate fine-grained search plans.

Graph Neural Networks for Databases: A Survey

Ziming Li, Youhuan Li, Yuyu Luo, Guoliang Li, Chuxu Zhang

International Joint Conference on Artificial Intelligence (IJCAI), Survey Track, 2025

paper

A structured and in-depth overview of how graph neural networks are applied inside database systems.

MatCo: Computing Match Cover of Subgraph Query over Graph Data

Zhichao Shi, Youhuan Li, Ziming Li, Yuequn Dou, Xionghu Zhong, Lei Zou

ACM SIGMOD International Conference on Management of Data (SIGMOD), 2025

paper code

Introduces the match cover of a subgraph query: a subset of answers whose vertices are exactly those covered by the entire answer set.

NewSP: A New Search Process for Continuous Subgraph Matching over Dynamic Graphs

Ziming Li, Youhuan Li, Xinhuan Chen, Lei Zou, Xiaofeng Yang, Yang Li, Hongbo Jiang

IEEE International Conference on Data Engineering (ICDE), 2024

paper code

A new search process for continuous subgraph matching with multi-expand, cache reuse, and adaptive check strategies.

VEND: Vertex Encoding for Edge Nonexistence Determination

Youhuan Li, Hangyu Zheng, Lei Zou, Xiaosen Li, Ziming Li, Pin Xiao, Yangyu Tao, Zheng Qin

IEEE International Conference on Data Engineering (ICDE), 2023

paper code

Vertex encodings that determine edge nonexistence so that no-result edge queries are never executed.