Meeting Planning on NatPlan meeting (test)
29AccuracyInduced
Evaluation Results
| Method | Links | |
|---|---|---|
| InducedLLM Backbone=DeepSeek-V32026.06 | 29 | |
| Induced2026.06 | 29 | |
| Chain-of-ThoughtLLM Backbone=DeepSeek-V32026.06 | 22 | |
| CoT2026.06 | 22 | |
| Agent Workflow MemoryLLM Backbone=DeepSeek-V32026.06 | 21 | |
| AWM2026.06 | 21 | |
| Hand-designedLLM Backbone=DeepSeek-V32026.06 | 14 | |
| Hand2026.06 | 14 | |
| Program-of-ThoughtsLLM Backbone=DeepSeek-V32026.06 | 9 | |
| Program-of-Thoughts2026.06 | 9 | |
| ReActLLM Backbone=DeepSeek-V32026.06 | 7 | |
| ReAct2026.06 | 7 |