List your company

Web Navigation and Task Automation on WebArena Continual-memory deployment

52.3Success Rate (SR)Auto-Dreamer
44.29246.37148.4550.529May 20, 2026

Evaluation results

MethodLinks
Auto-DreamerMemory Category=Ours, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview, Consolidator LLM=Qwen3-14B (SciWorld-trained)2026.0552.39270.628
AWMMemory Category=Workflow / procedural memory, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview2026.05528900.597
LightMemMemory Category=Two-timescale prompted, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview2026.0552370,8740.567
ExpeLMemory Category=Reflective / insight extraction, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview2026.0550.83,3710.576
MempMemory Category=Workflow / procedural memory, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview2026.0550.84,9730.574
Mem0Memory Category=Structured stores, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview2026.0550.343,3550.571
ReasoningBankMemory Category=Structured stores, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview2026.0549.824,3620.581
ReflexionMemory Category=Reflective / insight extraction, Frozen Task Agent LLM=Gemini-3-flash-preview, Memory-generation LLM=Gemini-3.1-flash-lite-preview2026.0546.48,1480.567
No memoryMemory Category=Baseline, Frozen Task Agent LLM=Gemini-3-flash-preview2026.0544.600.527