List your company

LLM Agent Performance on AgentBoard BabyAI Naive Stream

67.5Success Rate (1)ExpRAG
57.159.862.565.2Jun 1, 2026

Evaluation results

MethodLinks
ExpRAG2026.0667.576.77078.7
ReMem2026.0667.577.97079.2
MEMPROBE2026.0667.58072.580.4
ReAct2026.0657.572.957.572.9