2 papers
cs.AI2026
FDE-Gym: The Last Mile of AI Delivery
Dongxu Yang, Hongda Yan, Renxin Wang +23
Existing agent benchmarks typically evaluate agents on well-specified tasks defined by issue reports, specifications, or task tickets. Real-world customer delivery is different: fo…
cs.AI2026
PULSE: An Executable Contract Language for Spatiotemporal Knowledge Graph Engineering
Dongxu Yang, Ziyi Liang
Knowledge graph engineering often distributes accepted state, observations, constraints, processes, and hypothetical scenarios across artifacts whose combined execution contract re…