aiqbench analysis
This research addresses the challenge of aligning large language models' semantic reasoning with structured sequential generation for interpretable out-of-town point-of-interest recommendations. By integrating a fine-tuned LLM with a masked autoencoder and reinforcement learning, the proposed framework successfully grounds inferred travel styles into position-aware predictions while maintaining interpretability. The results demonstrate that this approach outperforms traditional recommenders and direct LLM baselines in generating coherent destination trajectories.
SemPOI-RL: Aligning LLM Semantic Reasoning for Interpretable Out-of-Town POI Sequential Generation
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 sequential generation remains challenging. This challenge is particularly evident in out-of-town (OOT) POI sequence generation, where a model must infer transferable travel intent from a user's hometown behaviors, adapt to cross-city interest drift, and generate a coherent destination trajectory under structural constraints. Existing approaches either rely on latent ID-based transfer with limited interpretability or directly use LLMs for sequence generation without explicitly grounding inferred semantics into position-aware predictions. To address this gap, we propose SemPOI-RL, a framework that aligns LLM semantic reasoning with structured sequence generation for interpretable OOT recommendation. Specifically, we first fine-tune an LLM to infer destination-oriented travel styles from users' hometown trajectories, using natural language as an interpretable semantic intermediate. We then introduce a Semantic POI Alignment Module (SPAM) to ground these inferred styles into a style-conditioned masked autoencoder for position-aware trajectory generation. Finally, we apply reinforcement learning with recommendation-oriented rewards to align LLM-generated styles with downstream sequence quality. Experiments on two real-world datasets show that SemPOI-RL consistently outperforms both traditional recommenders and direct LLM baselines, while providing interpretable style attribution across different phases of a trip. The code is available at https://github.com/Wind-Flipped/SemPOI-RL .
Abstract:Large language models (LLMs) exhibit strong semantic reasoning and open-ended generation abilities, but aligning these abilities with structured sequential generation remains challenging. This challenge is particularly evident in out-of-town (OOT) POI sequence generation, where a model must infer transferable travel intent from a user's hometown behaviors, adapt to cross-city interest drift, and generate a coherent destination trajectory under structural constraints. Existing approaches either rely on latent ID-based transfer with limited interpretability or directly use LLMs for sequence generation without explicitly grounding inferred semantics into position-aware predictions. To address this gap, we propose SemPOI-RL, a framework that aligns LLM semantic reasoning with structured sequence generation for interpretable OOT recommendation. Specifically, we first fine-tune an LLM to infer destination-oriented travel styles from users' hometown trajectories, using natural language as an interpretable semantic intermediate. We then introduce a Semantic POI Alignment Module (SPAM) to ground these inferred styles into a style-conditioned masked autoencoder for position-aware trajectory generation. Finally, we apply reinforcement learning with recommendation-oriented rewards to align LLM-generated styles with downstream sequence quality. Experiments on two real-world datasets show that SemPOI-RL consistently outperforms both traditional recommenders and direct LLM baselines, while providing interpretable style attribution across different phases of a trip. The code is available at this https URL .
Computation and Language (cs.CL); Artificial Intelligence (cs.AI)
arXiv:2608.30399 [cs.CL]
(or arXiv:2608.30399v1 [cs.CL] for this version)
https://doi.org/10.48550/arXiv.2608.30399 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 305 words
Related coverage
Game Design Creativity evals
LessWrong · Oct 12, 2026
Reasoning over Semantic IDs Enhances Generative Recommendation
arXiv · Jun 10, 2026
Semantic-Aligned Structural Abstraction for Multimodal Sentiment Analysis
arXiv · Jul 31, 2026
Jev: System One models for Prod, not God — with Diogo Almeida, CEO, TypeSafe AI
Latent Space · Sep 21, 2026