Wei Xie

The paper introduces an operator-level factorial benchmark for molecular MPNNs, finding that message construction (specifically concatenation-based mixing) is the primary determinant of performance, rather than the complexity of the node update mechanism.

PatchWorld introduces a gradient-free framework to create executable Python world models from offline trajectories, achieving high planning scores by inducing symbolic belief-state programs.

SkillRevise is an execution-grounded framework that iteratively refines initial, imperfect LLM agent skills by diagnosing defects from execution evidence and applying empirically validated edits, significantly boosting agent performance.