List your company

Interactive Agent Decision Making on ALFWorld Continual-memory deployment

60.2Success RateAuto-Dreamer
29.41637.40845.453.392May 20, 2026

Evaluation results

MethodLinks
Auto-DreamerMemory Category=Ours, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0560.210,95458.5
UMEMMemory Category=RL-trained writers, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0558.462,94756.4
Mem-αMemory Category=RL-trained writers, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Released 4B checkpoint2026.0557.4125,63556.6
ReflexionMemory Category=Reflective / insight extraction, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0549.211,96747.5
ExpeLMemory Category=Reflective / insight extraction, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0533.62,04230.6
AWMMemory Category=Workflow / procedural memory, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0532.816,84630.6
MempMemory Category=Workflow / procedural memory, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0531.46,73129.7
LightMemMemory Category=Two-timescale prompted, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0531.2130,00128.8
ReasoningBankMemory Category=Structured stores, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0531.142,78428.5
No memoryMemory Category=Baseline, Frozen Task Agent LLM=Qwen3.5-9B2026.0530.8028.7
Mem0Memory Category=Structured stores, Frozen Task Agent LLM=Qwen3.5-9B, Memory-generation LLM=Qwen3-14B2026.0530.6119,01327.9