Skip to content

armgit / camel

Public Imported from GitHub
0

🐫 CAMEL: The first and the best multi-agent framework. Finding the Scaling Law of Agents. https://www.camel-ai.org

chore : Update skill prompt in workforce (#3856)

Tao Sun855a1022a166
diff --git a/camel/societies/workforce/prompts.py b/camel/societies/workforce/prompts.py
index 07ec37cfb..241143588 100644
--- a/camel/societies/workforce/prompts.py
+++ b/camel/societies/workforce/prompts.py
@@ -229,6 +229,7 @@ TASK_DECOMPOSE_PROMPT = r"""You need to either decompose a complex task or enhan
* Treat the task as a single enhanced task.
* Preserve the original task intent and requirements. Clarify wording if needed, but do NOT add new deliverables or change the scope.
* Assume the executing worker will load and use the required skill via the SkillToolkit.
+ * Only decompose the task when no single skill can complete it end-to-end, and the task genuinely requires multiple agents using different skills to complete it*
These principles aim to reduce overall completion time by maximizing concurrent work and effectively utilizing all available worker capabilities.