arXiv:2606. 15315v1 Announce Type: new Abstract: Personalized public transit routing in public transit systems remains challenging due to the difficulty of capturing and integrating diverse user preferences into routing algorithms.
arXiv:2602. 22638v2 Announce Type: replace Abstract: Route-planning agents powered by large language models (LLMs) have emerged as a promising paradigm for supporting everyday human mobility through natural language interaction and tool-mediated decision making.
SWRouter is a new routing method for multi‑turn large language model conversations that uses a similarity‑based context segmentation mechanism to construct prompts and a dual‑metric evaluation framework to separate construction accuracy from router performance. The approach addresses two key challenges in multi‑turn dialogue: preventing information loss or confusion during context construction and evaluating routing quality independently of prompt quality. Experiments on multi‑turn dialogue benchmarks show that SWRouter outperforms strong baselines, improving evaluation accuracy by 16.26% over the best individual large language model and by 8.22% over the Conv‑ID Context baseline.
arXiv:2603.04191v2 Announce Type: replace Abstract: Large Language Models (LLMs) are increasingly serving as personal assistants, where users may share individual preferences over extended interactio...
arXiv:2602. 12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to diverse users, yet existing prompt optimization methods primarily focus on task-level optimization while largely overlooking user-specific preferences and latent constraints of individual users.
The paper evaluates how Retrieval-Augmented Generation (RAG) can improve Large Language Model (LLM) predictions of travel mode choice. Four retrieval strategies—basic RAG, balanced retrieval, cross‑encoder re‑ranking, and a combination of balanced retrieval with cross‑encoder—are tested on three LLMs (GPT‑4o, o4‑mini, o3) using 2023 Puget Sound travel survey data. Results show that RAG boosts accuracy across models, with GPT‑4o plus balanced retrieval and cross‑encoder achieving 80.8% accuracy, surpassing traditional statistical and machine learning baselines and demonstrating strong zero‑shot transfer.
arXiv:2606. 06178v1 Announce Type: new Abstract: Large language models (LLMs) present a trade-off between performance and cost, where more powerful models incur greater expense.
arXiv:2606. 18774v1 Announce Type: new Abstract: We present RouteJudge, an online pairwise preference evaluation framework for LLM routing systems, with a public platform available at https://routejudge.
GMTRouter is a personalized large language model router that represents multi‑turn user‑LLM interactions as a heterogeneous graph with five node types—user, LLM, query, response, and turn—to preserve relational structure. Using a lightweight inductive graph learning framework and a user‑conditioned graph sampling mechanism, it captures user preferences from few‑shot data, enabling effective personalization without extensive fine‑tuning. Experiments show GMTRouter outperforms strong baselines, improving accuracy by up to 0.108 and AUC by 0.124, and adapts to new users with minimal data.
arXiv:2607. 10651v1 Announce Type: new Abstract: In large urban areas, planning multi-day travel itineraries is challenging due to the abundance of Points of Interest (POIs), diverse user preferences, and constraints such as opening hours.
The paper introduces VIBE‑Bench, a new benchmark designed to test personalized large language models (PLLMs) in a regime where user profile cues and query‑specific preferences do not share the same conceptual space, a situation termed profile‑preference conceptual misalignment (PRCM). VIBE‑Bench contains 3,504 personas, 12,239 dialogues, and a manually verified gold test set, and includes two psychology‑grounded tasks that require cross‑concept preference reasoning beyond surface semantic overlap. Experiments show that existing PLLMs largely depend on shallow semantic correlations and struggle to learn robust cross‑concept mappings, highlighting PRCM as a distinct failure mode for personalization models.
arXiv:2511. 09373v2 Announce Type: replace-cross Abstract: LLMs now tackle a wide range of software-related tasks, yet we show that their performance varies markedly both across and within these tasks.
arXiv:2603.04445v3 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) with diverse capabilities, costs, and domains has created a critical need for intelligent mo...