Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Model

2026-04-15

AI Summary

This work addresses the limitation of conventional local lifestyle service recommendation methods, which treat user intent recognition and service recommendation as disjoint tasks, hindering unified modeling. To overcome this, we propose the first large language model–based joint framework that simultaneously optimizes lifestyle need prediction and service recommendation. Our approach enhances robustness by filtering behavioral noise through clustering, and integrates curriculum learning with reinforcement learning guided by verifiable rewards to progressively train the model in reasoning from need generation to service selection. Experimental results demonstrate significant improvements in both need prediction accuracy and recommendation performance, with notably strong generalization capabilities in long-tail scenarios.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: (Large) Language Models

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Local life service recommendation is distinct from general recommendation scenarios due to its strong living need-driven nature. Fundamentally, accurately identifying a user's immediate living need and recommending the corresponding service are inextricably linked tasks. However, prior works typically treat them in isolation, failing to achieve a unified modeling of need prediction and service recommendation. In this paper, we propose a novel large language model based framework that jointly performs living need prediction and service recommendation. To address the challenge of noise in raw consumption data, we introduce a behavioral clustering approach that filters out accidental factors and selectively preserves typical patterns. This enables the model to learn a robust logical basis for need generation and spontaneously generalize to long-tail scenarios. To navigate the vast search space stemming from diverse needs, merchants, and complex mapping paths, we employ a curriculum learning strategy combined with reinforcement learning with verifiable rewards. This approach guides the model to sequentially learn the logic from need generation to category mapping and specific service selection. Extensive experiments demonstrate that our unified framework significantly enhances both living need prediction performance and recommendation accuracy, validating the effectiveness of jointly modeling living needs and user behaviors.

Problem

• local life service recommendation
• living need prediction
• unified modeling
• user behavior
• recommendation accuracy

Innovation

• Agentic Reasoning
• Behavioral Clustering
• Curriculum Learning
• Reinforcement Learning
• Joint Modeling