CoS: Towards Optimal Event Scheduling via Chain-of-Scheduling

2025-11-16

AI Summary

This paper addresses the NP-hard event scheduling recommendation problem in Event-Based Social Networks (EBSNs), aiming to maximize user preference under temporal and geographical constraints. We propose CoS, a chain-based scheduling framework that employs an atomic three-stage process—exploration, verification, and integration—guided by knowledge distillation to enable large language models (LLMs) to autonomously generate interpretable, end-to-end event scheduling chains. Our approach jointly optimizes recommendation quality and computational efficiency. Methodologically, CoS is the first to leverage LLMs for zero-shot, end-to-end scheduling chain generation and achieves strong cross-domain generalization without task-specific fine-tuning. Extensive experiments on three real-world EBSN datasets demonstrate that CoS consistently approaches the theoretical optimum, significantly outperforming state-of-the-art baselines in both recommendation accuracy and efficiency, while maintaining superior scalability and generalization across diverse domains.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems

Abstract

Recommending event schedules is a key issue in Event-based Social Networks (EBSNs) in order to maintain user activity. An effective recommendation is required to maximize the user's preference, subjecting to both time and geographical constraints. Existing methods face an inherent trade-off among efficiency, effectiveness, and generalization, due to the NP-hard nature of the problem. This paper proposes the Chain-of-Scheduling (CoS) framework, which activates the event scheduling capability of Large Language Models (LLMs) through a guided, efficient scheduling process. CoS enhances LLM by formulating the schedule task into three atomic stages, i.e., exploration, verification and integration. Then we enable the LLMs to generate CoS autonomously via Knowledge Distillation (KD). Experimental results show that CoS achieves near-theoretical optimal effectiveness with high efficiency on three real-world datasets in a interpretable manner. Moreover, it demonstrates strong zero-shot learning ability on out-of-domain data.

Problem

• Optimizing event scheduling in social networks under constraints
• Balancing efficiency, effectiveness, and generalization trade-offs
• Enhancing LLMs for interpretable scheduling with zero-shot learning

Innovation

• Chain-of-Scheduling framework activates LLMs scheduling capability
• Formulates scheduling into exploration verification integration stages
• Enables autonomous CoS generation via Knowledge Distillation