List your company

Embodied Agent Task on ScienceWorld Seen

70.9Success RateGRPO w/ EVU
4.75621.92839.156.272Apr 19, 2026

Evaluation results

MethodLinks
GRPO w/ EVUMethod Category=Training, Backbone Model=Qwen2.5-3B-Instruct, Base Method=GRPO, EVU Mechanism=Included2026.0470.9
PPO w/ EVUMethod Category=Training, Backbone Model=Qwen3-1.7B-Instruct, Base Method=PPO, EVU Mechanism=Included2026.0462.9
ReAct w/ EVUMethod Category=Prompting, Backbone Model=DeepSeek V3.2, Base Method=ReAct, EVU Mechanism=Included2026.0462.3
ReActMethod Category=Prompting, Backbone Model=DeepSeek V3.2, Base Method=ReAct, EVU Mechanism=None2026.0460.3
PPO w/ EVUMethod Category=Training, Backbone Model=Qwen2.5-3B-Instruct, Base Method=PPO, EVU Mechanism=Included2026.0460.3
Plan-and-Act w/ EVUMethod Category=Prompting, Backbone Model=DeepSeek V3.2, Base Method=Plan-and-Act, EVU Mechanism=Included2026.0458.3
NoThinking w/ EVUMethod Category=Prompting, Backbone Model=DeepSeek V3.2, Base Method=NoThinking, EVU Mechanism=Included2026.0455
Plan-and-ActMethod Category=Prompting, Backbone Model=DeepSeek V3.2, Base Method=Plan-and-Act, EVU Mechanism=None2026.0455
PPOMethod Category=Training, Backbone Model=Qwen2.5-3B-Instruct, Base Method=PPO, EVU Mechanism=None2026.0453.6
GRPOMethod Category=Training, Backbone Model=Qwen2.5-3B-Instruct, Base Method=GRPO, EVU Mechanism=None2026.0449.7
SFT w/ EVUMethod Category=Training, Backbone Model=Qwen2.5-3B-Instruct, Base Method=SFT, EVU Mechanism=Included2026.0449
GRPO w/ EVUMethod Category=Training, Backbone Model=Qwen3-1.7B-Instruct, Base Method=GRPO, EVU Mechanism=Included2026.0447.7
NoThinkingMethod Category=Prompting, Backbone Model=DeepSeek V3.2, Base Method=NoThinking, EVU Mechanism=None2026.0447
GRPOMethod Category=Training, Backbone Model=Qwen3-1.7B-Instruct, Base Method=GRPO, EVU Mechanism=None2026.0441.7
PPOMethod Category=Training, Backbone Model=Qwen3-1.7B-Instruct, Base Method=PPO, EVU Mechanism=None2026.0437
SFT w/ EVUMethod Category=Training, Backbone Model=Qwen3-1.7B-Instruct, Base Method=SFT, EVU Mechanism=Included2026.0423.2
SFTMethod Category=Training, Backbone Model=Qwen2.5-3B-Instruct, Base Method=SFT, EVU Mechanism=None2026.0419.9
SFTMethod Category=Training, Backbone Model=Qwen3-1.7B-Instruct, Base Method=SFT, EVU Mechanism=None2026.047.3