Reflexion Retry Decision
Problem Statement
In a Reflexion loop, the agent retries a task after reflecting on failures, but only while it has retries left and the evaluation score is improving. Decide whether to attempt another try.
Background
Given the current attempt number (1-indexed), a max_attempts cap, the list of scores observed so far (one per attempt, higher is better), and a target threshold: retry only if the latest score is below threshold, attempts remain, and the latest score strictly improved over the previous attempt (or it is the first attempt). No improvement means reflection isn't helping — stop.
Your Task
def should_retry(scores, attempt, max_attempts, threshold):
Return True to retry, else False.
Input Format
- scores (list of floats, len == attempt), attempt (int), max_attempts (int), threshold (float).
Output Format
- A boolean.
Sample
print(should_retry([0.4, 0.6], 2, 4, 0.9))
Output:
True
Example
Input
print(should_retry([0.4, 0.6], 2, 4, 0.9))
Output
True
Reasoning
- Extract the most recent performance metric from the score history to evaluate current standing: .
- Verify if the agent has met the success criteria by comparing the latest score against the target: since , the performance is insufficient, so the retry process continues.
- Check if the attempt limit has been reached to ensure resources remain: with and , the condition holds, indicating retries are still permitted.
- Determine if the reflection strategy is effective by checking for strict improvement over the previous attempt: comparing the latest score to the prior score , we see , confirming positive progress.
- Since the score is below the threshold, attempts remain, and performance is improving, the decision is made to proceed with another try.
- The final output is True
Constraints
- Retry requires: latest score < threshold,
attempt < max_attempts, and improvement over previous (first attempt counts as improving). scoreshas one entry per attempt so far.- Return a bool.
Learn this in
The Agent Loop & ReAct FoundationsAgent Engineering Study PlanProduction: Observability, Benchmarks, Runtimes & Eval-Driven DevelopmentAgent Engineering Study PlanSelf-Improvement: Reflexion, Self-Refine, Tree-of-Thought, LATSAgent Engineering Study PlanWorkflow Patterns & LangGraph Stateful GraphsAgent Engineering Study Plan