List your company

Embodied Task Execution on ALFWorld

93.28Success RateEmbodiSkill w/ GPT-5.2
2.300825.920449.5473.1596Feb 3, 2026Feb 19, 2026Mar 7, 2026Mar 23, 2026Apr 8, 2026Apr 24, 2026May 11, 2026

Evaluation results

MethodLinks
EmbodiSkill w/ GPT-5.2Executor=Qwen3.5-27B, Skill Evolution Model=GPT-5.22026.0593.28—95.8396.7773.9195.24100100
EmbodiSkill w/ Gemini-3-flashExecutor=Qwen3.5-27B, Skill Evolution Model=Gemini-3-flash2026.0587.31—95.8393.5569.5795.2483.3382.35
EmbodiSkill w/ GPT-5.2Executor=Qwen2.5-14B-Instruct, Skill Evolution Model=GPT-5.22026.0586.57—91.6796.7773.9195.2483.3370.59
EmbodiSkill w/ Gemini-3-flashExecutor=Qwen2.5-14B-Instruct, Skill Evolution Model=Gemini-3-flash2026.0585.82—79.1793.5573.9190.4810076.47
Gemini-3-flashExecutor=Gemini-3-flash2026.0582.09—91.6783.8765.2285.7183.3382.35
G-MemoryExecutor=Qwen3.5-27B, Memory Mechanism=G-Memory2026.0574.62—62.577.4282.6185.7183.3352.94
GPT-5.2Executor=GPT-5.22026.0570.89—87.567.7456.5276.1983.3352.94
G-MemoryExecutor=Qwen2.5-14B-Instruct, Memory Mechanism=G-Memory2026.0567.16—5083.8769.5785.7183.3317.65
Mem0Executor=Qwen3.5-27B, Memory Mechanism=Mem02026.0564.18—62.561.2956.5285.7172.2247.06
LangMemExecutor=Qwen3.5-27B, Memory Mechanism=LangMem2026.0562.69—62.561.2952.1776.1972.2252.94
No memoryExecutor=Qwen3.5-27B, Memory Mechanism=None2026.0561.19—66.6751.6165.2276.1972.2235.29
No memoryExecutor=Qwen2.5-14B-Instruct, Memory Mechanism=None2026.0546.27—33.3351.6126.0985.7172.225.88
LangMemExecutor=Qwen2.5-14B-Instruct, Memory Mechanism=LangMem2026.0536.57—12.532.2626.0971.4383.330
MiniMax-M2.1Intervention Mechanism=Rollback, Calibration=Uncalibrated2026.0216.60.5——————
MiniMax-M2.1Intervention Mechanism=Append, Calibration=Calibrated2026.0216.50.5——————
MiniMax-M2.1Intervention Mechanism=Baseline, Calibration=N/A2026.0216.10.5——————
GLM-4.7Intervention Mechanism=Rollback, Calibration=Uncalibrated2026.0215.81.1——————
MiniMax-M2.1Intervention Mechanism=Rollback, Calibration=Calibrated2026.0215.80.5——————
GLM-4.7Intervention Mechanism=Append, Calibration=Uncalibrated2026.0215.31.1——————
MiniMax-M2.1Intervention Mechanism=Append, Calibration=Uncalibrated2026.0215.30.5——————
GLM-4.7Intervention Mechanism=Rollback, Calibration=Calibrated2026.02151.1——————
GLM-4.7Intervention Mechanism=Baseline, Calibration=N/A2026.0214.71.1——————
GLM-4.7Intervention Mechanism=Append, Calibration=Calibrated2026.0213.41.1——————
Mem0Executor=Qwen2.5-14B-Instruct, Memory Mechanism=Mem02026.0512.69—004.35088.890
Qwen-3-8BIntervention Mechanism=Append, Calibration=Uncalibrated2026.028.62.8——————
Qwen-3-8BIntervention Mechanism=Rollback, Calibration=Uncalibrated2026.027.92.8——————
Qwen-3-8BIntervention Mechanism=Append, Calibration=Calibrated2026.027.82.8——————
Qwen-3-8BIntervention Mechanism=Rollback, Calibration=Calibrated2026.026.92.8——————
Qwen-3-8BIntervention Mechanism=Baseline, Calibration=N/A2026.025.82.8——————