List your company

General Question Answering on PopQA (test)

49.3EMWorkflow-R1-Search
10.71620.73330.7540.767Feb 1, 2026Feb 22, 2026Mar 16, 2026Apr 6, 2026Apr 28, 2026May 19, 2026Jun 10, 2026

Evaluation results

MethodLinks
Workflow-R1-SearchMulti-turn=true, Backbone=Qwen2.5-32B-Instruct2026.0249.3
ReCalRouting Strategy=RL-based Routing, Task Decomposition=false2026.0646.6
ReCal+Routing Strategy=RL-based Routing, Task Decomposition=false2026.0646.6
Search-R1 (GRPO)Multi-turn=true, Backbone=Qwen2.5-32B-Instruct2026.0242.7
Router-R1Routing Strategy=RL-based Routing, Task Decomposition=false2026.0640
Search-R1 (PPO)Multi-turn=true, Backbone=Qwen2.5-32B-Instruct2026.0239.7
RAGRouting Strategy=No Routing, Task Decomposition=false2026.0636.6
Largest LLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0635.4
Prompt LLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0634
Search-R1Routing Strategy=No Routing, Task Decomposition=false2026.0632.4
RouterDCRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0628.2
GraphRouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0628
Prompt LLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=true2026.0625.6
Workflow-R1Multi-turn=true, Backbone=Qwen2.5-32B-Instruct2026.0224.6
AFlowMulti-turn=false, Backbone=Qwen2.5-32B-Instruct2026.0223.2
KNN RouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=true2026.0623.2
KNN RouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0622.2
MLP RouterRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0622.2
SC (CoT×5)Multi-turn=false, Backbone=Qwen2.5-32B-Instruct2026.0221.4
MedPromptMulti-turn=false, Backbone=Qwen2.5-32B-Instruct2026.0221.1
CoTMulti-turn=false, Backbone=Qwen2.5-32B-Instruct2026.0220.5
MaASMulti-turn=false, Backbone=Qwen2.5-32B-Instruct2026.0219.3
RouteLLMRouting Strategy=Heuristic & Discriminative Routing, Task Decomposition=false2026.0619.2
CoTRouting Strategy=No Routing, Task Decomposition=false2026.0616
SFTRouting Strategy=No Routing, Task Decomposition=false2026.0616
DirectMulti-turn=false, Backbone=Qwen2.5-32B-Instruct2026.0213.3
VanillaRouting Strategy=No Routing, Task Decomposition=false2026.0612.2