List your company

Instruction Following on ALFWorld

89.3AccuracyM2CL
19.72437.78755.8573.913Feb 2, 2026

Evaluation results

MethodLinks
M2CLBackbone=Qwen-72B, Number of LLMs=322026.0289.3
M2CLBackbone=Llama-70B, Number of LLMs=322026.0288.5
M2CLModel=Llama-70B, Number of LLMs=162026.0284.9
M2CLModel=Qwen-72B, Number of LLMs=162026.0282.9
MacNetBackbone=Qwen-72B, Number of LLMs=322026.0270.5
MacNetModel=Qwen-72B, Number of LLMs=162026.0265.8
MacNetBackbone=Llama-70B, Number of LLMs=322026.0264.5
DebateBackbone=Qwen-72B, Number of LLMs=322026.0262.8
MacNetModel=Llama-70B, Number of LLMs=162026.0261.6
DebateModel=Qwen-72B, Number of LLMs=162026.0260.8
BoNBackbone=Qwen-72B, Number of LLMs=322026.0259.3
BoNModel=Qwen-72B, Number of LLMs=162026.0258.5
GPTSwarmBackbone=Qwen-72B, Number of LLMs=322026.0258.3
GPTSwarmModel=Qwen-72B, Number of LLMs=162026.0257.3
DyLANModel=Qwen-72B, Number of LLMs=162026.0256.1
DyLANBackbone=Qwen-72B, Number of LLMs=322026.0256
M2CLBackbone=Qwen-14B, Number of LLMs=322026.0254.9
BoNModel=Llama-70B, Number of LLMs=162026.0253.9
BoNBackbone=Llama-70B, Number of LLMs=322026.0253.1
DebateBackbone=Llama-70B, Number of LLMs=322026.0252.6
DebateModel=Llama-70B, Number of LLMs=162026.0252.2
M2CLBackbone=Llama-14B, Number of LLMs=322026.0252.2
GPTSwarmBackbone=Llama-70B, Number of LLMs=322026.0252.2
GPTSwarmModel=Llama-70B, Number of LLMs=162026.0251.7
M2CLModel=Qwen-14B, Number of LLMs=162026.0251.2
DyLANModel=Llama-70B, Number of LLMs=162026.0250.5
DyLANBackbone=Llama-70B, Number of LLMs=322026.0250.1
M2CLModel=Llama-14B, Number of LLMs=162026.0248.7
SingleModel=Qwen-72B, Number of LLMs=12026.0247.7
SingleBackbone=Qwen-72B, Number of LLMs=322026.0246.7
MacNetBackbone=Qwen-14B, Number of LLMs=322026.0244.8
M2CLBackbone=Qwen-7B, Number of LLMs=322026.0244.4
SingleModel=Llama-70B, Number of LLMs=12026.0243.7
SingleBackbone=Llama-70B, Number of LLMs=322026.0243.1
M2CLBackbone=Llama-7B, Number of LLMs=322026.0242.5
MacNetModel=Qwen-14B, Number of LLMs=162026.0242.1
M2CLModel=Qwen-7B, Number of LLMs=162026.0241.8
M2CLModel=Llama-7B, Number of LLMs=162026.0239.8
DebateBackbone=Qwen-14B, Number of LLMs=322026.0239
MacNetBackbone=Qwen-7B, Number of LLMs=322026.0238.6
BoNModel=Qwen-14B, Number of LLMs=162026.0238.1
DebateModel=Qwen-14B, Number of LLMs=162026.0237.7
BoNBackbone=Qwen-14B, Number of LLMs=322026.0237.4
MacNetBackbone=Llama-14B, Number of LLMs=322026.0237.1
GPTSwarmBackbone=Qwen-14B, Number of LLMs=322026.0236.4
MacNetBackbone=Llama-7B, Number of LLMs=322026.0235.7
GPTSwarmModel=Qwen-14B, Number of LLMs=162026.0235.5
MacNetModel=Qwen-7B, Number of LLMs=162026.0235.4
DyLANBackbone=Qwen-14B, Number of LLMs=322026.0235.4
DyLANModel=Qwen-14B, Number of LLMs=162026.0234.9
MacNetModel=Llama-14B, Number of LLMs=162026.0234.8
BoNModel=Llama-14B, Number of LLMs=162026.0233
BoNModel=Qwen-7B, Number of LLMs=162026.0232.9
MacNetModel=Llama-7B, Number of LLMs=162026.0232.8
BoNBackbone=Llama-14B, Number of LLMs=322026.0232.8
BoNBackbone=Qwen-7B, Number of LLMs=322026.0232.8
DyLANBackbone=Llama-14B, Number of LLMs=322026.0232.1
DebateModel=Llama-14B, Number of LLMs=162026.0232
DyLANModel=Llama-14B, Number of LLMs=162026.0231.9
DebateBackbone=Llama-14B, Number of LLMs=322026.0231.9
DebateModel=Qwen-7B, Number of LLMs=162026.0231.7
DebateBackbone=Qwen-7B, Number of LLMs=322026.0231.7
GPTSwarmBackbone=Qwen-7B, Number of LLMs=322026.0231.2
DyLANBackbone=Qwen-7B, Number of LLMs=322026.0230.7
DyLANModel=Qwen-7B, Number of LLMs=162026.0230.4
GPTSwarmModel=Qwen-7B, Number of LLMs=162026.0230.1
SingleBackbone=Qwen-14B, Number of LLMs=322026.0229.4
SingleModel=Qwen-14B, Number of LLMs=12026.0228.3
SingleModel=Llama-14B, Number of LLMs=12026.0227.4
GPTSwarmBackbone=Llama-7B, Number of LLMs=322026.0227.3
GPTSwarmModel=Llama-7B, Number of LLMs=162026.0227.2
SingleBackbone=Llama-14B, Number of LLMs=322026.0227
BoNBackbone=Llama-7B, Number of LLMs=322026.0226.8
BoNModel=Llama-7B, Number of LLMs=162026.0226.7
DebateBackbone=Llama-7B, Number of LLMs=322026.0226.4
DebateModel=Llama-7B, Number of LLMs=162026.0225.7
DyLANBackbone=Llama-7B, Number of LLMs=322026.0224.9
DyLANModel=Llama-7B, Number of LLMs=162026.0224.6
SingleBackbone=Qwen-7B, Number of LLMs=322026.0224.2
SingleModel=Qwen-7B, Number of LLMs=12026.0223.4
SingleModel=Llama-7B, Number of LLMs=12026.0222.4
SingleBackbone=Llama-7B, Number of LLMs=322026.0222.4