List your company

Embodied Reasoning on ALFWorld

0.96AccuracyStudent (IC+Cascade)
0.293360.466430.63950.81257Dec 2, 2025Dec 12, 2025Dec 22, 2025Jan 2, 2026Jan 12, 2026Jan 22, 2026Feb 2, 2026

Evaluation results

MethodLinks
Student (IC+Cascade)Model=GPT-4.1-mini, In-Context Distillation=true, Self-Consistency Cascade=true2025.120.960.41
Student (IC+Cascade)Model=Llama-3.3-70B, In-Context Distillation=true, Self-Consistency Cascade=true2025.120.930.21
M2CLModel=Qwen-72B, Number of LLMs=642026.020.929—
M2CLModel=Llama-70B, Number of LLMs=642026.020.908—
TeacherModel=Sonnet 4.52025.120.891
Student (IC)Model=GPT-4.1-mini, In-Context Distillation=true2025.120.870.43
Student (IC)Model=Llama-3.3-70B, In-Context Distillation=true2025.120.870.14
M2CLBackbone=Qwen-72B, Number of LLMs=82026.020.79—
M2CLBackbone Model=Qwen-72B, Number of LLMs=42026.020.79—
M2CLBackbone=Llama-70B, Number of LLMs=82026.020.789—
MacNetModel=Qwen-72B, Number of LLMs=642026.020.744—
M2CLBase Model=Qwen-72B, Number of LLMs=42026.020.739—
M2CLBase Model=Llama-70B, Number of LLMs=42026.020.695—
MacNetModel=Llama-70B, Number of LLMs=642026.020.679—
DebateModel=Qwen-72B, Number of LLMs=642026.020.625—
MacNetBackbone=Qwen-72B, Number of LLMs=82026.020.618—
MacNetBackbone Model=Qwen-72B, Number of LLMs=42026.020.618—
DebateBackbone=Qwen-72B, Number of LLMs=82026.020.604—
DebateBackbone Model=Qwen-72B, Number of LLMs=42026.020.604—
BoNModel=Qwen-72B, Number of LLMs=642026.020.601—
GPTSwarmModel=Qwen-72B, Number of LLMs=642026.020.596—
DebateBase Model=Qwen-72B, Number of LLMs=42026.020.583—
BoNBackbone=Qwen-72B, Number of LLMs=82026.020.575—
Best-of-N (BoN)Backbone Model=Qwen-72B, Number of LLMs=42026.020.575—
MacNetBackbone=Llama-70B, Number of LLMs=82026.020.573—
MacNetBase Model=Qwen-72B, Number of LLMs=42026.020.572—
DyLANModel=Qwen-72B, Number of LLMs=642026.020.569—
GPTSwarmBackbone=Qwen-72B, Number of LLMs=82026.020.568—
GPTSwarmBackbone Model=Qwen-72B, Number of LLMs=42026.020.568—
BoNBase Model=Qwen-72B, Number of LLMs=42026.020.566—
M2CLModel=Qwen-14B, Number of LLMs=642026.020.564—
GPTSwarmBase Model=Qwen-72B, Number of LLMs=42026.020.552—
DyLANBackbone=Qwen-72B, Number of LLMs=82026.020.551—
DyLANBackbone Model=Qwen-72B, Number of LLMs=42026.020.551—
M2CLModel=Llama-14B, Number of LLMs=642026.020.548—
BoNModel=Llama-70B, Number of LLMs=642026.020.548—
DyLANBase Model=Qwen-72B, Number of LLMs=42026.020.542—
DebateModel=Llama-70B, Number of LLMs=642026.020.536—
MacNetBase Model=Llama-70B, Number of LLMs=42026.020.527—
BoNBackbone=Llama-70B, Number of LLMs=82026.020.524—
GPTSwarmModel=Llama-70B, Number of LLMs=642026.020.524—
DebateBackbone=Llama-70B, Number of LLMs=82026.020.517—
GPTSwarmBackbone=Llama-70B, Number of LLMs=82026.020.514—
GPTSwarmBase Model=Llama-70B, Number of LLMs=42026.020.51—
BoNBase Model=Llama-70B, Number of LLMs=42026.020.509—
DyLANModel=Llama-70B, Number of LLMs=642026.020.504—
DebateBase Model=Llama-70B, Number of LLMs=42026.020.504—
DyLANBackbone=Llama-70B, Number of LLMs=82026.020.502—
Student (ZS)Model=Llama-3.3-70B, Zero-shot=true2025.120.50.11
DyLANBase Model=Llama-70B, Number of LLMs=42026.020.493—
SingleBase Model=Qwen-72B, Number of LLMs=12026.020.493—
M2CLBackbone=Qwen-14B, Number of LLMs=82026.020.482—
SingleBackbone=Qwen-72B, Number of LLMs=82026.020.482—
M2CLBackbone Model=Qwen-14B, Number of LLMs=42026.020.482—
Single executionBackbone Model=Qwen-72B, Number of LLMs=42026.020.482—
MacNetModel=Qwen-14B, Number of LLMs=642026.020.475—
M2CLModel=Qwen-7B, Number of LLMs=642026.020.468—
SingleModel=Qwen-72B, Number of LLMs=642026.020.467—
M2CLBackbone=Llama-14B, Number of LLMs=82026.020.461—
SingleBase Model=Llama-70B, Number of LLMs=12026.020.461—
M2CLBase Model=Qwen-14B, Number of LLMs=42026.020.45—
M2CLModel=Llama-7B, Number of LLMs=642026.020.442—
SingleBackbone=Llama-70B, Number of LLMs=82026.020.441—
SingleModel=Llama-70B, Number of LLMs=642026.020.43—
M2CLBase Model=Llama-14B, Number of LLMs=42026.020.429—
MacNetModel=Qwen-7B, Number of LLMs=642026.020.416—
M2CLBackbone=Qwen-7B, Number of LLMs=82026.020.399—
M2CLBackbone Model=Qwen-7B, Number of LLMs=42026.020.399—
MacNetBackbone=Qwen-14B, Number of LLMs=82026.020.392—
MacNetBackbone Model=Qwen-14B, Number of LLMs=42026.020.392—
MacNetModel=Llama-14B, Number of LLMs=642026.020.391—
MacNetModel=Llama-7B, Number of LLMs=642026.020.388—
DebateModel=Qwen-14B, Number of LLMs=642026.020.388—
BoNModel=Qwen-14B, Number of LLMs=642026.020.384—
BoNBackbone=Qwen-14B, Number of LLMs=82026.020.375—
Best-of-N (BoN)Backbone Model=Qwen-14B, Number of LLMs=42026.020.375—
M2CLBackbone=Llama-7B, Number of LLMs=82026.020.372—
DebateBackbone=Qwen-14B, Number of LLMs=82026.020.368—
DebateBackbone Model=Qwen-14B, Number of LLMs=42026.020.368—
M2CLBase Model=Qwen-7B, Number of LLMs=42026.020.367—
DyLANModel=Qwen-14B, Number of LLMs=642026.020.362—
BoNBase Model=Qwen-14B, Number of LLMs=42026.020.362—
MacNetBase Model=Qwen-14B, Number of LLMs=42026.020.361—
GPTSwarmModel=Qwen-14B, Number of LLMs=642026.020.359—
DebateBase Model=Qwen-14B, Number of LLMs=42026.020.356—
M2CLBase Model=Llama-7B, Number of LLMs=42026.020.351—
GPTSwarmBackbone=Qwen-14B, Number of LLMs=82026.020.349—
GPTSwarmBackbone Model=Qwen-14B, Number of LLMs=42026.020.349—
DyLANBackbone=Qwen-14B, Number of LLMs=82026.020.348—
DyLANBackbone Model=Qwen-14B, Number of LLMs=42026.020.348—
GPTSwarmBase Model=Qwen-14B, Number of LLMs=42026.020.346—
BoNModel=Qwen-7B, Number of LLMs=642026.020.345—
MacNetBackbone=Qwen-7B, Number of LLMs=82026.020.336—
MacNetBackbone Model=Qwen-7B, Number of LLMs=42026.020.336—
DyLANBase Model=Qwen-14B, Number of LLMs=42026.020.336—
MacNetBackbone=Llama-14B, Number of LLMs=82026.020.334—
BoNModel=Llama-14B, Number of LLMs=642026.020.326—
DebateModel=Llama-14B, Number of LLMs=642026.020.326—
DebateModel=Qwen-7B, Number of LLMs=642026.020.323—
BoNBackbone=Llama-14B, Number of LLMs=82026.020.319—