AI Insights

• Ii Agent Identity: Describes the role and expertise of agent Ai. [3]
• Oi Objective Function: Optimization goal pursued by agent Ai. [3]
• The paper presents a framework for multi-constraint travel planning called TourPlanner. [2]

Abstract
Travel planning is a sophisticated decision-making process that requires synthesizing multifaceted information to construct itineraries. However, existing travel planning approaches face several challenges: (1) Pruning candidate points of interest (POIs) while maintaining a high recall rate; (2) A single reasoning path restricts the exploration capability within the feasible solution space for travel planning; (3) Simultaneously optimizing hard constraints and soft constraints remains a significant difficulty. To address these challenges, we propose TourPlanner, a comprehensive framework featuring multi-path reasoning and constraint-gated reinforcement learning. Specifically, we first introduce a Personalized Recall and Spatial Optimization (PReSO) workflow to construct spatially-aware candidate POIs' set. Subsequently, we propose Competitive consensus Chain-of-Thought (CCoT), a multi-path reasoning paradigm that improves the ability of exploring the feasible solution space. To further refine the plan, we integrate a sigmoid-based gating mechanism into the reinforcement learning stage, which dynamically prioritizes soft-constraint satisfaction only after hard constraints are met. Experimental results on travel planning benchmarks demonstrate that TourPlanner achieves state-of-the-art performance, significantly surpassing existing methods in both feasibility and user-preference alignment.

Why we are recommending this paper?
Due to your Interest in Travel Itinerary Creation

This paper directly addresses the complexities of travel planning, a core interest, by proposing a framework for itinerary creation. The use of reinforcement learning and constraint-gated approaches aligns with the user's interest in personalized and optimized travel recommendations.

Abstract
We study the problem of personalization in large language models (LLMs). Prior work predominantly represents user preferences as implicit, model-specific vectors or parameters, yielding opaque ``black-box'' profiles that are difficult to interpret and transfer across models and tasks. In contrast, we advocate natural language as a universal, model- and task-agnostic interface for preference representation. The formulation leads to interpretable and reusable preference descriptions, while naturally supporting continual evolution as new interactions are observed. To learn such representations, we introduce a two-stage training framework that combines supervised fine-tuning on high-quality synthesized data with reinforcement learning to optimize long-term utility and cross-task transferability. Based on this framework, we develop AlignXplore+, a universal preference reasoning model that generates textual preference summaries. Experiments on nine benchmarks show that our 8B model achieves state-of-the-art performanc -- outperforming substantially larger open-source models -- while exhibiting strong transferability across tasks, model families, and interaction formats.

Why we are recommending this paper?
Due to your Interest in Travel Personalization

Given the focus on personalization, this paper’s exploration of using LLMs for user preferences is highly relevant. Understanding how to transfer personalization across models aligns with the user’s interest in tailored travel experiences.

Abstract
Recent years have witnessed success of sequential modeling, generative recommender, and large language model for recommendation. Though the scaling law has been validated for sequential models, it showed inefficiency in computational capacity when considering real-world applications like recommendation, due to the non-linear(quadratic) increasing nature of the transformer model. To improve the efficiency of the sequential model, we introduced a novel approach to sequential recommendation that leverages personalization techniques to enhance efficiency and performance. Our method compresses long user interaction histories into learnable tokens, which are then combined with recent interactions to generate recommendations. This approach significantly reduces computational costs while maintaining high recommendation accuracy. Our method could be applied to existing transformer based recommendation models, e.g., HSTU and HLLM. Extensive experiments on multiple sequential models demonstrate its versatility and effectiveness. Source code is available at \href{https://github.com/facebookresearch/PerSRec}{https://github.com/facebookresearch/PerSRec}.

Why we are recommending this paper?
Due to your Interest in Travel Personalization

This paper’s focus on sequential recommendation and long-term user interest is directly applicable to travel planning. The work’s exploration of scaling laws for recommendation systems aligns with the user's interest in sophisticated travel ranking and planning.

Abstract
Digital twins and other simulators are increasingly used to support routing decisions in large-scale networks. However, simulator outputs often exhibit systematic bias, while ground-truth measurements are costly and scarce. We study a stochastic shortest-path problem in which a planner has access to abundant synthetic samples, limited real-world observations, and an edge-similarity structure capturing expected behavioral similarity across links. We model the simulator-to-reality discrepancy as an unknown, edge-specific bias that varies smoothly over the similarity graph, and estimate it using Laplacian-regularized least squares. This approach yields calibrated edge cost estimates even in data-scarce regimes. We establish finite-sample error bounds, translate estimation error into path-level suboptimality guarantees, and propose a computable, data-driven certificate that verifies near-optimality of a candidate route. For cold-start settings without initial real data, we develop a bias-aware active learning algorithm that leverages the simulator and adaptively selects edges to measure until a prescribed accuracy is met. Numerical experiments on multiple road networks and traffic graphs further demonstrate the effectiveness of our methods.

Why we are recommending this paper?
Due to your Interest in Travel Search

The paper's investigation into shortest path learning, particularly in data-scarce environments, is pertinent to travel planning and route optimization. This directly supports the user's interest in travel search and efficient travel planning.

Abstract
Search engines are commonly used for online political information seeking. Yet, it remains unclear how search query suggestions for political searches that reflect the latent interest of internet users vary across countries and over time. We provide a systematic analysis of Google search engine query suggestions for European and national politicians. Using an original dataset of search query suggestions for European politicians collected in ten countries, we find that query suggestions are less stable over time in politicians' countries of origin, when the politicians hold a supranational role, and for female politicians. Moreover, query suggestions for political leaders and male politicians are more similar across countries. We conclude by discussing possible future directions for studying information search about European politicians in online search.

Why we are recommending this paper?
Due to your Interest in Travel Search

This research examines search engine query patterns, which is a key aspect of understanding user intent and information seeking behavior. Given the user's interest in travel recommendations and travel search, this paper offers valuable insights.