List your company

Web Task on WebShop

69.2Average RewardCo-Evolving Agents
3.1620.30537.4554.595Nov 9, 2023Mar 12, 2024Jul 15, 2024Nov 17, 2024Mar 22, 2025Jul 25, 2025Nov 27, 2025

Evaluation results

MethodLinks
Co-Evolving AgentsModel=Llama-2-13B-chat2025.1169.2
Co-Evolving AgentsAdaptation=Fine-tuning, Backbone=Llama-2-7B-Chat2025.1166.7
ETOModel=Llama-2-13B-chat2025.1165
Llama-2-7B-Chat + PPOAdaptation=Fine-tuning, Backbone=Llama-2-7B-Chat2025.1164.2
GPT-4Adaptation=In-context2025.1163.2
Llama-2-7B-Chat + ETOAdaptation=Fine-tuning, Backbone=Llama-2-7B-Chat2025.1163
GPT-3.5-TurboAdaptation=In-context2025.1162.4
Llama-2-7B-Chat + RFTAdaptation=Fine-tuning, Backbone=Llama-2-7B-Chat2025.1161.3
SFTModel=Llama-2-13B-chat2025.1159.3
Llama-2-7B-Chat + SFTAdaptation=Fine-tuning, Backbone=Llama-2-7B-Chat2025.1159.2
LUMOS-IAll-13Bshot=2-/3-shot2023.1150.3
Claude-instant2023.1149.7
LUMOS-IQA-13Bshot=2-/3-shot2023.1147.3
OpenChat-v3.2-13B2023.1146.9
LUMOS-IWeb-13Bshot=2-/3-shot2023.1146.2
LUMOS-IMath-13Bshot=2-/3-shot2023.1145.7
LUMOS-IMM-13Bshot=2-/3-shot2023.1143.8
Vicuna-v1.5-13B2023.1141.7
Vicuna-v1.3-33B2023.1123.9
ChatGLM22023.1119.4
Vicuna-v1.1-13B2023.1112.6
WizardLM-30B2023.1110.6
Koala-13B2023.116
Baichuan-13B-chat2023.115.7