3 papers
cs.AI2026
ST-Bench: A Spatial-Temporal Benchmark for Multi-Agent System Generation on Scientific Research Tasks
Qi Cheng, Rongchao Dong, Shengyu Chen +8
The rapid progress of LLM-based multi-agent systems (MAS) has shown that they largely outperform single agents on coding, math, and QA tasks, where executable tests provide a binar…
cs.LG2026
CHAM-net: A Contrastive Hierarchical Adaptive Meta-network for Robust Global Methane Flux Prediction
Rongchao Dong, Yiming Sun, Shuo Chen +4
Methane is a potent greenhouse gas that significantly contributes to global warming. However, accurately estimating global methane emissions and consumption remains challenging due…
cs.LG2026
Role-Aware Conditional Inference for Spatiotemporal Ecosystem Carbon Flux Prediction
Yiming Sun, Runlong Yu, Rongchao Dong +6
Accurate prediction of terrestrial ecosystem carbon fluxes (e.g., CO, GPP, and CH) is essential for understanding the global carbon cycle and managing its impacts. However,…