code-act
code-act copied to clipboard
Official Repo for ICML 2024 paper "Executable Code Actions Elicit Better LLM Agents" by Xingyao Wang, Yangyi Chen, Lifan Yuan, Yizhe Zhang, Yunzhu Li, Hao Peng, Heng Ji.
Hello, I’ve been using CodeAct integrated with GPT-4o for a chatbot interface. I noticed that the model doesn't seem to maintain context across separate API calls within the same session....
What are the prompt formats of the two models you provided on hugging face?
Thanks for your great work! I am interested in the CodeAct framework and would like to reproduce Table 2 in the original paper, the results of atomic API call correctness...
Is it possible to replace the llm from the 2 provided open source options to other models from openai or clause to compare performance. Found the method to serve for...
https://mistral.ai/news/codestral/