List your company

Question Answering on GAIA (test)

41.7Unreliability RateKbSD
39.431254.745670.0685.3744Jun 29, 2026

Evaluation results

MethodLinks
KbSDBackbone=Qwen2.5-7B, Paradigm=RL-based Agentic RAG2026.0641.7
KbSDBackbone=Qwen2.5-3B, Paradigm=RL-based Agentic RAG2026.0658.1
KbPOBackbone=Qwen2.5-7B, Paradigm=RL-based Agentic RAG2026.0671.9
KbPOBackbone=Qwen2.5-3B, Paradigm=RL-based Agentic RAG2026.0677.2
Search-R1Backbone=Qwen2.5-7B, Paradigm=RL-based Agentic RAG2026.0689.92
ARPOBackbone=Qwen2.5-7B, Paradigm=RL-based Agentic RAG2026.0691.44
TCRAGBackbone=Qwen2.5-7B, Paradigm=Agentic RAG2026.0691.79
ARPOBackbone=Qwen2.5-3B, Paradigm=RL-based Agentic RAG2026.0692.29
COTBackbone=Qwen2.5-3B, Paradigm=No RAG2026.0692.98
Mem1Backbone=Qwen2.5-7B, Paradigm=RL-based Agentic RAG2026.0693.5
ReACTBackbone=Qwen2.5-7B, Paradigm=Agentic RAG2026.0693.63
COTBackbone=Qwen2.5-7B, Paradigm=No RAG2026.0693.83
BaseBackbone=Qwen2.5-3B, Paradigm=No RAG2026.0694.3
TCRAGBackbone=Qwen2.5-3B, Paradigm=Agentic RAG2026.0694.47
IRCOTBackbone=Qwen2.5-7B, Paradigm=Agentic RAG2026.0694.5
FS-RAGBackbone=Qwen2.5-7B, Paradigm=Naive RAG2026.0694.98
AEPOBackbone=Qwen2.5-3B, Paradigm=RL-based Agentic RAG2026.0694.99
ReACTBackbone=Qwen2.5-3B, Paradigm=Agentic RAG2026.0695.22
Search-R1Backbone=Qwen2.5-3B, Paradigm=RL-based Agentic RAG2026.0695.32
FL-RAGBackbone=Qwen2.5-7B, Paradigm=Naive RAG2026.0695.4
ReSearchBackbone=Qwen2.5-3B, Paradigm=RL-based Agentic RAG2026.0695.52
ReSearchBackbone=Qwen2.5-7B, Paradigm=RL-based Agentic RAG2026.0695.57
FS-RAGBackbone=Qwen2.5-3B, Paradigm=Naive RAG2026.0695.7
BaseBackbone=Qwen2.5-7B, Paradigm=No RAG2026.0695.71
IRCOTBackbone=Qwen2.5-3B, Paradigm=Agentic RAG2026.0697.23
AEPOBackbone=Qwen2.5-7B, Paradigm=RL-based Agentic RAG2026.0697.35
Mem1Backbone=Qwen2.5-3B, Paradigm=RL-based Agentic RAG2026.0697.53
FL-RAGBackbone=Qwen2.5-3B, Paradigm=Naive RAG2026.0698.42