← Search

Qiuning Wei

2 accepted papers

2026

Counterfactual Planning for Generalizable Agents’ Actions

AAAI 2026technical

Large language models have revolutionized agent planning by serving as the engine of heuristic guidance. However, LLM-based agents often struggle to generalize across complex environments and to adapt to stochastic feedback arising from environment–action interactions. We propose Counterfactual Plan

Cited by 0SourcePDFScholar
2026

FlowMAP: Flow Matching for Generalizable Agent Planning

ICML 2026poster

Agent planning faces dynamic heterogeneity—nonstationary observations, dynamics, and objectives with sparse, delayed rewards—which dominant methods largely ignore, leading to poor generalization under environment shifts. We propose Flow-Matching for Agent Planning (FlowMAP), which formulates plannin…

Cited by 0SourceScholar