Abstract
Mainstream ranking approaches typically follow a Generator-Evaluator two-stage paradigm, where a generator produces candidate lists and an evaluator selects the best one. Recent work has attempted to enhance performance by expanding the number of candidate lists, for example, through multi-generator settings. However, ranking involves selecting a recommendation list from a combinatorially large space. Simply enlarging the candidate set remains ineffective, and performance gains quickly saturate. At the same time, recent advances in large recommendation models have shown that end-to-end one-stage models can achieve promising performance with the expectation of scaling laws. Motivated by this, we revisit ranking from a generator-only one-stage perspective. We theoretically prove that, for any (finite Multi-)Generator-Evaluator model, there always exists a generator-only model that achieves strictly smaller approximation error to the optimal ranking policy, while also enjoying scaling laws as its size increases. Building on this result, we derive an evidence upper bound of the one-stage optimization objective, from which we find that one can leverage a reward model trained on real user feedback to construct a reference policy in a group-relative manner. This reference policy serves as a practical surrogate of the optimal policy, enabling effective training of a large generator-only ranker. Based on these insights, we propose GoalRank, a generator-only ranking framework. Extensive offline experiments on public benchmarks and large-scale online A/B tests demonstrate that GoalRank consistently outperforms state-of-the-art methods.

Abstract
We introduce the upward rank mobility curve as a new measure of intergenerational mobility that captures upward movements across the entire parental income distribution. Our approach extends Bhattacharya and Mazumder (2011) by conditioning on a single parental income rank, thereby eliminating aggregation bias. We show that the measure can be characterized solely by the copula of parent and child income, and we propose a nonparametric copula-based estimator with better properties than kernel-based alternatives. For a conditional version of the measure without such a representation, we develop a two-step semiparametric estimator based on distribution regression and establish its asymptotic properties. An application to U.S. data reveals that whites exhibit significant upward mobility dominance over blacks among lower-middle-income families.

Abstract
Recent advances in multimodal large language models (MLLMs) have significantly enhanced video understanding capabilities, opening new possibilities for practical applications. Yet current video benchmarks focus largely on indoor scenes or short-range outdoor activities, leaving the challenges associated with long-distance travel largely unexplored. Mastering extended geospatial-temporal trajectories is critical for next-generation MLLMs, underpinning real-world tasks such as embodied-AI planning and navigation. To bridge this gap, we present VIR-Bench, a novel benchmark consisting of 200 travel videos that frames itinerary reconstruction as a challenging task designed to evaluate and push forward MLLMs' geospatial-temporal intelligence. Experimental results reveal that state-of-the-art MLLMs, including proprietary ones, struggle to achieve high scores, underscoring the difficulty of handling videos that span extended spatial and temporal scales. Moreover, we conduct an in-depth case study in which we develop a prototype travel-planning agent that leverages the insights gained from VIR-Bench. The agent's markedly improved itinerary recommendations verify that our evaluation protocol not only benchmarks models effectively but also translates into concrete performance gains in user-facing applications.

AI Insights

• Kyoto’s itinerary balances intimate moments with quiet reflection, making it a perfect romantic getaway.
• A generous $1,964 budget lets travelers indulge in local cuisine ($1,064), comfortable lodging ($500), and enriching activities ($300).
• The plan cleverly mixes efficient public transport with strategic taxi rides to maximize every minute.
• Practical tips include carrying cash, using a Suica/ICOCA card, packing light layers, and respecting photography rules.
• Geisha Culture is defined as a traditional Japanese art form of music, dance, and poetry performed in Kyoto’s Gion district.
• Spiritual Legacy refers to the cultural and historical significance of Kyoto’s temples and shrines.
• For deeper insight, read “Kyoto’s Cultural Heritage: A Study on its Preservation and Promotion” and explore Japan Guide online.

Abstract
Travel planning (TP) agent has recently worked as an emerging building block to interact with external tools and resources for travel itinerary generation, ensuring enjoyable user experience. Despite its benefits, existing studies rely on hand craft prompt and fixed agent workflow, hindering more flexible and autonomous TP agent. This paper proposes DeepTravel, an end to end agentic reinforcement learning framework for building autonomous travel planning agent, capable of autonomously planning, executing tools, and reflecting on tool responses to explore, verify, and refine intermediate actions in multi step reasoning. To achieve this, we first construct a robust sandbox environment by caching transportation, accommodation and POI data, facilitating TP agent training without being constrained by real world APIs limitations (e.g., inconsistent outputs). Moreover, we develop a hierarchical reward modeling system, where a trajectory level verifier first checks spatiotemporal feasibility and filters unsatisfied travel itinerary, and then the turn level verifier further validate itinerary detail consistency with tool responses, enabling efficient and precise reward service. Finally, we propose the reply augmented reinforcement learning method that enables TP agent to periodically replay from a failures experience buffer, emerging notable agentic capacity. We deploy trained TP agent on DiDi Enterprise Solutions App and conduct comprehensive online and offline evaluations, demonstrating that DeepTravel enables small size LLMs (e.g., Qwen3 32B) to significantly outperform existing frontier LLMs such as OpenAI o1, o3 and DeepSeek R1 in travel planning tasks.

Abstract
Large language model (LLM) personalization aims to tailor model behavior to individual users based on their historical interactions. However, its effectiveness is often hindered by two key challenges: the \textit{cold-start problem}, where users with limited history provide insufficient context for accurate personalization, and the \textit{biasing problem}, where users with abundant but skewed history cause the model to overfit to narrow preferences. We identify both issues as symptoms of a common underlying limitation, i.e., the inability to model collective knowledge across users. To address this, we propose a local-global memory framework (LoGo) that combines the personalized local memory with a collective global memory that captures shared interests across the population. To reconcile discrepancies between these two memory sources, we introduce a mediator module designed to resolve conflicts between local and global signals. Extensive experiments on multiple benchmarks demonstrate that LoGo consistently improves personalization quality by both warming up cold-start users and mitigating biased predictions. These results highlight the importance of incorporating collective knowledge to enhance LLM personalization.

Abstract
Solving Traveling Salesman Problem (TSP) is NP-hard yet fundamental for wide real-world applications. Classical exact methods face challenges in scaling, and heuristic methods often require domain-specific parameter calibration. While learning-based approaches have shown promise, they suffer from poor generalization and limited scalability due to fixed training data. This work proposes ViTSP, a novel framework that leverages pre-trained vision language models (VLMs) to visually guide the solution process for large-scale TSPs. The VLMs function to identify promising small-scale subproblems from a visualized TSP instance, which are then efficiently optimized using an off-the-shelf solver to improve the global solution. ViTSP bypasses the dedicated model training at the user end while maintaining effectiveness across diverse instances. Experiments on real-world TSP instances ranging from 1k to 88k nodes demonstrate that ViTSP consistently achieves solutions with average optimality gaps below 0.2%, outperforming existing learning-based methods. Under the same runtime budget, it surpasses the best-performing heuristic solver, LKH-3, by reducing its gaps by 12% to 100%, particularly on very-large-scale instances with more than 10k nodes. Our framework offers a new perspective in hybridizing pre-trained generative models and operations research solvers in solving combinatorial optimization problems, with practical implications for integration into more complex logistics systems. The code is available at https://anonymous.4open.science/r/ViTSP_codes-6683.

Abstract
This paper introduces a novel capacitated Two-Echelon Location-Routing Problem with Eco-conscious Customer Behavior (2E-LRP-ECB) aimed at enhancing the environmental sustainability of last-mile delivery (LMD) operations. The model jointly optimizes dynamic satellites location, vehicle routing, and customer delivery modes, explicitly accounting for (i) heterogeneous customer travel behaviors, (ii) heterogeneous fleet composition, and (iii) diverse emission profiles across both echelons. A piecewise linear formulation captures the additional emissions from first-echelon vehicle stops, while customer travel emissions are computed based on individual willingness and capacity to use zero-emission transport. The problem is solved exactly for a wide set of real-world-based instances under four operational strategies, differing in optimization objectives and second-echelon fleet composition. Computational experiments, including a case study with a major Portuguese LMD provider, highlight the environmental and operational tradeoffs inherent to strategic and operational choices such as fleet composition, satellite activation, and customer pick-up policies. Results reveal that minimizing distance can lead to substantial increases in emissions, while emissions-oriented strategies leverage customer travel to achieve significant sustainability gains without compromising service efficiency. A multi-objective analysis using the epsilon-constraint method produces Pareto frontiers and knee-point solutions, offering actionable insights for balancing operational efficiency and environmental impact in sustainable LMD design.