Multi-Agent Path Finding on MAPF-FrozenLake 4-agent 4x4
49.33Valid RateQwen3-4B + GRPO + LLM-as-Environment-Engineer
Evaluation Results
| Method | Links | ||
|---|---|---|---|
| Qwen3-4B + GRPO + LLM-as-Environment-EngineerBackbone=Qwen3-4B, Training=GRPO, Environment Design=Ours2026.06 | 49.33 | 32 | |
| Grok-4.22026.06 | 48 | 34 | |
| Kimi-K2.52026.06 | 44.67 | 28.67 | |
| Qwen3-4B + GRPO (random)Backbone=Qwen3-4B, Training=GRPO, Config=single randomly sampled Round-02026.06 | 42.67 | 27.33 | |
| GPT-5.42026.06 | 35.33 | 22 | |
| Gemini-3.1-Pro2026.06 | 28.67 | 22.67 | |
| Qwen3-4B (base)Backbone=Qwen3-4B, Status=untrained2026.06 | 10.67 | 9.33 |