mirror of
https://github.com/agentscope-ai/ReMe.git
synced 2026-09-23 00:43:18 +00:00
32 lines
No EOL
1.1 KiB
YAML
32 lines
No EOL
1.1 KiB
YAML
summary_prompt: |
|
|
# Execution Process A
|
|
{execution_process_a}
|
|
|
|
# Execution Process B
|
|
{execution_process_b}
|
|
|
|
# Task
|
|
**Execution Process A** and **Execution Process B** represent two distinct execution trajectories of two agents, with Execution Process A being superior to Execution Process B.
|
|
Analyze these two trajectories and identify areas where Execution Process B can be improved relative to Execution Process A.
|
|
The insights derived should be generalizable, offering guidance for solving similar problems in the future.
|
|
These insights can include positive recommendations or point out pitfalls to avoid.
|
|
The format of the insights can be plain text or a snippet of code addressing a specific issue.
|
|
If no insights can be derived, return an empty list [].
|
|
For each insight, first specify the context in which it applies (when to use), followed by the insight itself. Provide up to two insights.
|
|
|
|
# Output Format
|
|
{summary_example}
|
|
|
|
summary_example: |
|
|
```json
|
|
[
|
|
{
|
|
"when_to_use": "...",
|
|
"experience": "..."
|
|
},
|
|
{
|
|
"when_to_use": "...",
|
|
"experience": "..."
|
|
}
|
|
]
|
|
``` |