A self-evolving LLM agent retrieves hierarchical historical strategies from an experience tree and iteratively tunes them through online A/B feedback, reporting a 4.829% GMV lift in deployment.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing
A self-evolving LLM agent retrieves hierarchical historical strategies from an experience tree and iteratively tunes them through online A/B feedback, reporting a 4.829% GMV lift in deployment.