List your company

Question Answering on HotpotQA (Acc)

90.38AccuracyDMoA
21.240839.190457.1475.0896Mar 26, 2026Apr 10, 2026Apr 25, 2026May 10, 2026May 25, 2026Jun 9, 2026Jun 25, 2026

Evaluation results

MethodLinks
DMoABackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0590.38
AFlowBackbone=gpt-oss-120b2026.0590.04
STEERBackbone=gpt-oss-120b2026.0589.35
SpecReasonBackbone=gpt-oss-120b2026.0588.29
G-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0587.66
SafeSieveBackbone=gpt-oss-120b2026.0587.22
ARG-DesignerBackbone=gpt-oss-120b, Evaluation Paradigm=few-shot2026.0586.45
GPTSwarmBackbone=gpt-oss-120b2026.0585.4
LLM-DebateBackbone=gpt-oss-120b2026.0584.55
Random GraphBackbone=gpt-oss-120b2026.0584.28
MoABackbone=gpt-oss-120b2026.0584.02
StarBackbone=gpt-oss-120b2026.0583.52
Complete GraphBackbone=gpt-oss-120b2026.0583.35
AutoGenBackbone=gpt-oss-120b2026.0583.25
VanillaBackbone=gpt-oss-120b2026.0582.35
SCBackbone=gpt-oss-120b2026.0582.24
TreeBackbone=gpt-oss-120b2026.0581.5
CoTBackbone=gpt-oss-120b2026.0581.04
ChainBackbone=gpt-oss-120b2026.0580.77
FE-SFT & FC-RLBackbone=Youtu-LLM-2B-Base, Framework=WM-AMT, Optimization Stage=RL stage2026.0659
FE-SFT & RLBackbone=Youtu-LLM-2B-Base, Framework=WM-AMT, Optimization Stage=RL stage2026.0657
FE-SFT & RL*Backbone=Youtu-LLM-2B-Base, Framework=Standard, Optimization Stage=RL stage2026.0655.4
State-SFT & RL†Backbone=Youtu-LLM-2B-Base, Framework=Standard, Optimization Stage=RL stage2026.0655.2
IWM & RLBackbone=Youtu-LLM-2B-Base, Framework=Standard, Optimization Stage=RL stage2026.0655
State-SFT & RL‡Backbone=Youtu-LLM-2B-Base, Framework=WM-AMT, Optimization Stage=RL stage2026.0654.6
SFT & RL*Backbone=Youtu-LLM-2B-Base, Framework=Standard, Optimization Stage=RL stage2026.0653.8
SFT & RLBackbone=Youtu-LLM-2B-Base, Framework=WM-AMT, Optimization Stage=RL stage2026.0653.6
IWMBackbone=Youtu-LLM-2B-Base, Framework=Standard, Optimization Stage=SFT stage2026.0646
FE-SFTBackbone=Youtu-LLM-2B-Base, Framework=WM-AMT, Optimization Stage=SFT stage2026.0645.8
SFT*Backbone=Youtu-LLM-2B-Base, Framework=Standard, Optimization Stage=SFT stage2026.0644.8
SFTBackbone=Youtu-LLM-2B-Base, Framework=WM-AMT, Optimization Stage=SFT stage2026.0644.6
Naive RAGLLM=Llama-3.1-8B, Write-back=true2026.0343.56
RePlugLLM=Llama-3.1-8B, Write-back=true2026.0343.12
Naive RAGLLM=Llama-3.1-8B, Write-back=false2026.0342.33
FE-SFT*Backbone=Youtu-LLM-2B-Base, Framework=Standard, Optimization Stage=SFT stage2026.0642.2
RePlugLLM=Llama-3.1-8B, Write-back=false2026.0342.12
Naive RAGLLM=Gemma-3-12B, Write-back=true2026.0341.99
RePlugLLM=Gemma-3-12B, Write-back=true2026.0341.97
Naive RAGLLM=Gemma-3-12B, Write-back=false2026.0341.13
RePlugLLM=Gemma-3-12B, Write-back=false2026.0341.13
FLARELLM=Llama-3.1-8B, Write-back=true2026.0332.12
FLARELLM=Llama-3.1-8B, Write-back=false2026.0331.25
Self-RAGLLM=Llama-3.1-8B, Write-back=true2026.0331.04
FLARELLM=Gemma-3-12B, Write-back=true2026.0330.18
FLARELLM=Gemma-3-12B, Write-back=false2026.0329.82
Self-RAGLLM=Llama-3.1-8B, Write-back=false2026.0329.33
Self-RAGLLM=Gemma-3-12B, Write-back=true2026.0328.73
Self-RAGLLM=Gemma-3-12B, Write-back=false2026.0327.49
No RetrievalLLM=Gemma-3-12B2026.0324.28
No RetrievalLLM=Llama-3.1-8B2026.0323.9