List your company
ResearchFormerly WizWand

Dialogue Agent Interaction on DEMO Collaboration set

8.65Goal Achievement ScoreLlama3.1-8B-Instruct w/ AMPO
7.52687.81848.118.4016May 4, 2025
Updated 8mo ago

Evaluation results

MethodLinks
Llama3.1-8B-Instruct w/ AMPOInteraction Partner=GPT-4o, Base Model=Llama3.1-8B-Instruct2025.058.65
Llama3.1-8B-InstructInteraction Partner=GPT-4o, Base Model=Llama3.1-8B-Instruct2025.058.56
Llama3.1-8B-Instruct w/ GRPOInteraction Partner=GPT-4o, Base Model=Llama3.1-8B-Instruct2025.058.35
Llama3.1-8B-Instruct w/ AMPOInteraction Partner=Claude-3.5-Sonnet, Base Model=Llama3.1-8B-Instruct2025.058.12
Llama3.1-8B-Instruct w/ GRPOInteraction Partner=Claude-3.5-Sonnet, Base Model=Llama3.1-8B-Instruct2025.058.09
Qwen2.5-7B-Instruct w/ AMPOInteraction Partner=GPT-4o, Base Model=Qwen2.5-7B-Instruct2025.057.95
Qwen2.5-7B-Instruct w/ GRPOInteraction Partner=GPT-4o, Base Model=Qwen2.5-7B-Instruct2025.057.9
Llama3.1-8B-InstructInteraction Partner=Claude-3.5-Sonnet, Base Model=Llama3.1-8B-Instruct2025.057.89
Qwen2.5-7B-Instruct w/ AMPOInteraction Partner=Claude-3.5-Sonnet, Base Model=Qwen2.5-7B-Instruct2025.057.82
Qwen2.5-7B-Instruct w/ GRPOInteraction Partner=Claude-3.5-Sonnet, Base Model=Qwen2.5-7B-Instruct2025.057.81
Qwen2.5-7B-InstructInteraction Partner=GPT-4o, Base Model=Qwen2.5-7B-Instruct2025.057.73
Qwen2.5-7B-InstructInteraction Partner=Claude-3.5-Sonnet, Base Model=Qwen2.5-7B-Instruct2025.057.57