List your company

Interactive Embodied Instruction Following on ALFWorld In-domain

97ScoreTask-Perturbed NLL Optimization
81.485.4589.593.55Jun 25, 2026

Evaluation results

MethodLinks
Task-Perturbed NLL OptimizationBackbone=Qwen3-8B2026.0697
GRPOBackbone=Qwen3-8B2026.0695
Task-Perturbed NLL OptimizationBackbone=Qwen3-4B2026.0686
GRPOBackbone=Qwen3-4B2026.0682