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:2608.30399v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities, but aligning these abilities with structured sequ...
arXiv:2606. 01046v1 Announce Type: new Abstract: The development of Large Language Models (LLMs) has significantly improved travel planning applications, yet evaluating such models is limited by existing benchmarks' limitations: 1) overemphasis on constraint compliance, neglecting multi-dimensional qualities like spatio-temporal cost; 2) datasets lacking real-world authenticity and coverage in key areas (e.
The paper evaluates two strategies for training language‑model‑based world models—fine‑tuning and Retrieval Augmented Generation (RAG)—across five diverse environments. Fine‑tuning generally yields higher rewards, while RAG is more data‑efficient. The authors propose a counterfactual error estimation for RAG, improve retrieval with a hierarchical query reformulation, and combine both approaches into a hybrid system that outperforms each method alone.
arXiv:2608. 20320v1 Announce Type: new Abstract: Travel behavior research increasingly combines digital data collection with predictive modeling, yet these stages are often developed and evaluated separately.
The paper demonstrates that fine‑tuning large language models (LLMs) on local tourist trajectory data can predict visitor movements under varying conditions. Using 566 trajectories from Wakayama Castle Park, Japan, the authors fine‑tuned Llama‑3.1‑8B, achieving 49.1% accuracy for next point‑of‑interest predictions and maintaining strong performance even on undersampled scenarios such as rainy days. This shows that LLMs can serve as high‑fidelity, context‑aware behavior models for tourist prediction and enable counterfactual analysis of mobility interventions.
arXiv:2509.09710v3 Announce Type: replace-cross Abstract: This study introduces a Large Language Model (LLM) scheme for generating key attributes of travel diaries in agent-based transportation model...
The paper introduces the concept of LLM‑specific utility, defining it as the performance gain a target large language model (LLM) achieves when provided with a passage compared to answering without evidence. A benchmark of utilitarian passages is built for four LLMs (Qwen3‑8B/14B/32B and Llama 3.1‑8B) across three QA datasets, revealing that each model benefits most from its own tailored evidence and that evidence optimized for other models is consistently suboptimal. The authors also create SpecUBench, a benchmark for LLM‑specific utility judgment, and show that current utility‑aware retrieval methods largely capture model‑agnostic usefulness, struggling to estimate LLM‑specific utility. "whyItMatters":"The study demonstrates that retrieval‑augmented generation must consider model‑specific evidence selection to truly improve LLM performance, highlighting a gap in existing utility‑aware methods."
arXiv:2510. 14819v3 Announce Type: replace-cross Abstract: Trajectory representation learning (TRL) aims to encode raw trajectory data into low-dimensional embeddings for downstream tasks such as travel time estimation, mobility prediction, and trajectory similarity analysis.
Behavior2Trip introduces a new task—Behavior‑Aware Travel Planning—where user preferences are inferred from past behavior trajectories rather than explicit instructions. The benchmark contains 11,400 instances from a major Chinese travel platform, each with nearly 40 recorded behaviors across 14 attributes and 5 preference dimensions. A reinforcement‑learning agent, B2T‑Agent, leverages these trajectories, external retrieval tools, and internal memory, outperforming GPT‑4.1 and other baselines on the dataset.
The paper introduces MARI, a Memory-Augmented Recommendation system that uses a Decision Memory Bank to store Structured Decision Memories (SDMs) capturing users’ goals, constraints, and trade-offs. Unlike prior methods that flatten heterogeneous behaviors into token sequences, MARI retrieves relevant SDMs to enhance LLM reasoning, improving performance on next-item prediction and a new Difficult Choice Prediction task while keeping latency low. The approach also provides interpretable, human-readable insights into user decision-making.
arXiv:2610.01936v2 Announce Type: replace Abstract: Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across natural language tasks but remain fundamentally limited by...
PACIFIC is a framework that aligns large language model responses with user preferences by leveraging stable Big‑Five personality traits as a latent signal. The authors built a 1,200‑pair dataset covering diverse domains and trait directions, and found that trait‑aligned contexts enable LLMs to achieve near‑ceiling accuracy (up to 99%) in personalized QA. They also introduced a persona‑aware contrastive retriever (PiRAG) that improves label‑free accuracy from 30% to 43% over standard semantic retrieval, highlighting retrieval as the main bottleneck.