andre/crewAI
1
0
Fork 0
mirror of https://github.com/crewAIInc/crewAI.git synced 2026-01-10 00:28:31 +00:00
Code Issues Actions 1 Packages Projects Releases Wiki Activity

Implement LLM-based adaptive reasoning with function calling

Browse Source 
Co-Authored-By: Joe Moura <joao@crewai.com>
This commit is contained in:
Devin AI
2025-05-27 08:35:32 +00:00
parent 5868ac71dd
commit 203faa6a77
4 changed files with 155 additions and 21 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
docs/concepts/reasoning.mdx
View File

@@ -108,13 +108,12 @@ This creates a predictable pattern of reflection during task execution, which is
### Adaptive Reasoning
The adaptive reasoning feature uses contextual triggers to determine when reasoning should occur:
The adaptive reasoning feature uses LLM function calling to determine when reasoning should occur:
1. **Multiple tools used**: When the agent has used multiple different tools in recent steps, indicating a change in approach
2. **Long execution**: When the task is taking longer than expected (iterations > max_iter/2)
3. **Error detection**: When recent messages contain error indicators like "error", "exception", "failed", etc.
1. **LLM-based decision**: The agent's LLM evaluates the current execution context (task description, expected output, steps taken so far) to decide if reasoning is needed
2. **Error detection fallback**: When recent messages contain error indicators like "error", "exception", "failed", etc., reasoning is automatically triggered
This creates a more dynamic reasoning pattern that adapts to the task's needs, allowing the agent to be more responsive to changing conditions.
This creates an intelligent reasoning pattern where the agent uses its own judgment to determine when strategic reassessment would be most beneficial, while maintaining automatic error recovery.
### Mid-execution Reasoning Process