5 papers
SimSkill: A Self-Evolving LLM Agent for Skill and Knowledge Accumulation in Traffic Simulation
Qi Liu, Qinzheng Wang, Can Li +2
Cumulative culture enables humans to preserve, reuse, and extend knowledge and skills across experiences and generations. Inspired by this principle, we introduce \textit{SimSkill}…
OR-Agent: Bridging Evolutionary Search and Structured Research for Automated Heuristic Design
Qi Liu, Ruochen Hao, Can Li +1
Automating heuristic design in complex, experiment-driven domains requires more than iterative mutation of solution algorithms. Current LLM-based evolutionary methods often rely on…
GATSim: Urban Mobility Simulation with Generative Agents
Qi Liu, Can Li, Wanjing Ma
Traditional agent-based urban mobility simulations often rely on rigid rulebased systems that struggle to capture the complexity, adaptability, and behavioral diversity inherent in…
Navigating Data Corruption in Machine Learning: Balancing Quality, Quantity, and Imputation Strategies
Qi Liu, Wanjing Ma
Data corruption, including missing and noisy data, poses significant challenges in real-world machine learning. This study investigates the effects of data corruption on model perf…
The Epochal Sawtooth Phenomenon: Unveiling Training Loss Oscillations in Adam and Other Optimizers
Qi Liu, Wanjing Ma
In this paper, we identify and analyze a recurring training loss pattern, which we term the \textit{Epochal Sawtooth Phenomenon (ESP)}, commonly observed during training with adapt…