List your company

Interactive Instruction Following on ALFWorld OOD

92Success RateTask-Perturbed NLL Optimization
23.56841.33459.176.866Feb 2, 2026Feb 25, 2026Mar 21, 2026Apr 14, 2026May 8, 2026Jun 1, 2026Jun 25, 2026

Evaluation results

MethodLinks
Task-Perturbed NLL OptimizationBackbone=Qwen3-8B2026.0692
ProcMEM2026.0290.9
AWM2026.0290
GRPOBackbone=Qwen3-8B2026.0686
G-Memory2026.0281.2
Expel2026.0274
ReAct2026.0264
A-MEM2026.0264
CoT2026.0262
Task-Perturbed NLL OptimizationBackbone=Qwen3-4B2026.0662
GRPOBackbone=Qwen3-4B2026.0644
RAG2026.0240.2
State2026.0226.2