Paper

{
  "raw_xml": "<entry>\n    <id>http://arxiv.org/abs/2602.21634v1</id>\n    <title>AgentLTV: An Agent-Based Unified Search-and-Evolution Framework for Automated Lifetime Value Prediction</title>\n    <updated>2026-02-25T06:58:18Z</updated>\n    <link href='https://arxiv.org/abs/2602.21634v1' rel='alternate' type='text/html'/>\n    <link href='https://arxiv.org/pdf/2602.21634v1' rel='related' title='pdf' type='application/pdf'/>\n    <summary>Lifetime Value (LTV) prediction is critical in advertising, recommender systems, and e-commerce. In practice, LTV data patterns vary across decision scenarios. As a result, practitioners often build complex, scenario-specific pipelines and iterate over feature processing, objective design, and tuning. This process is expensive and hard to transfer. We propose AgentLTV, an agent-based unified search-and-evolution framework for automated LTV modeling. AgentLTV treats each candidate solution as an {executable pipeline program}. LLM-driven agents generate code, run and repair pipelines, and analyze execution feedback. Two decision agents coordinate a two-stage search. The Monte Carlo Tree Search (MCTS) stage explores a broad space of modeling choices under a fixed budget, guided by the Polynomial Upper Confidence bounds for Trees criterion and a Pareto-aware multi-metric value function. The Evolutionary Algorithm (EA) stage refines the best MCTS program via island-based evolution with crossover, mutation, and migration. Experiments on a large-scale proprietary dataset and a public benchmark show that AgentLTV consistently discovers strong models across ranking and error metrics. Online bucket-level analysis further indicates improved ranking consistency and value calibration, especially for high-value and negative-LTV segments. We summarize practitioner-oriented takeaways: use MCTS for rapid adaptation to new data patterns, use EA for stable refinement, and validate deployment readiness with bucket-level ranking and calibration diagnostics. The proposed AgentLTV has been successfully deployed online.</summary>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.LG'/>\n    <category scheme='http://arxiv.org/schemas/atom' term='cs.MA'/>\n    <published>2026-02-25T06:58:18Z</published>\n    <arxiv:comment>12 pages, 4 figures, submitted to KDD 2026: 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining, ADS Track</arxiv:comment>\n    <arxiv:primary_category term='cs.LG'/>\n    <author>\n      <name>Chaowei Wu</name>\n    </author>\n    <author>\n      <name>Huazhu Chen</name>\n    </author>\n    <author>\n      <name>Congde Yuan</name>\n    </author>\n    <author>\n      <name>Qirui Yang</name>\n    </author>\n    <author>\n      <name>Guoqing Song</name>\n    </author>\n    <author>\n      <name>Yue Gao</name>\n    </author>\n    <author>\n      <name>Li Luo</name>\n    </author>\n    <author>\n      <name>Frank Youhua Chen</name>\n    </author>\n    <author>\n      <name>Mengzhuo Guo</name>\n    </author>\n  </entry>"
}