Mathematical Reasoning on AMC 23 (avg@16, pass@16)
89.5avg@16Dr. MAS
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Dr. MASBackbone=Qwen3-4B, Agent Setting=Multi-Agent & LLM Non-Sharing2026.02 | 89.5 | 97.5 | |
| Dr. MASBackbone=Qwen3-8B, Agent Setting=Multi-Agent & LLM Sharing2026.02 | 88.9 | 97.5 | |
| Dr. MASBackbone=Qwen3-8B, Agent Setting=Multi-Agent & LLM Non-Sharing2026.02 | 87.5 | 95 | |
| Dr. MASBackbone=Qwen3-4B, Agent Setting=Multi-Agent & LLM Sharing2026.02 | 87.3 | 95 | |
| GRPOBackbone=Qwen3-8B, Agent Setting=Multi-Agent & LLM Sharing2026.02 | 87.3 | 95 | |
| GRPOBackbone=Qwen3-8B, Agent Setting=Single-Agent2026.02 | 87 | 95 | |
| GRPOBackbone=Qwen3-8B, Agent Setting=Multi-Agent & LLM Non-Sharing2026.02 | 86.1 | 95 | |
| GRPOBackbone=Qwen3-4B, Agent Setting=Multi-Agent & LLM Sharing2026.02 | 85.6 | 95 | |
| GRPOBackbone=Qwen3-4B, Agent Setting=Single-Agent2026.02 | 83.5 | 95 | |
| GRPOBackbone=Qwen3-4B, Agent Setting=Multi-Agent & LLM Non-Sharing2026.02 | 83.5 | 95 |