ROAM: Retrieval-Augmented Optimization for Feasible Multi-Day Itinerary Planning

Large language models (LLMs) can draft plausible travel itineraries, but the plans they produce are frequently infeasible: attractions are grouped into days without regard for geography, opening hours are ignored, and a single generation pass cannot reliably organize a multi-day trip. We present ROAM, a retrieval-augmented agentic framework for spontaneous multi-day itinerary planning that…

arxiv.org ·2d ago

We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.

Read the original at arxiv.org →

More in AI

Analysis: AI sell-off leaves markets at a crossroad

A rout in AI and tech stocks has wiped trillions off global markets. For City AM’s Midday Markets newsletter, Ali Lyon chews over what it all means. It’s been one of those mornings when analysts have woken up and reached for their morbid bon mots of choice. “Bloodbath” has proven popular. So too, “capitulation-level event” [...]

2d ago ·cityam.com

Hideo Kojima says AI can’t replace human craftsmanship in video games

Celebrated game director Hideo Kojima says AI mustn’t replace human craftsmanship in the creative industries.

2d ago ·techradar.com

Tesla to wind down Cybertruck production as Elon Musk focuses on robotics and AI

Decision made in order for factory in Texas to be used for Cybercab, the carmaker’s self-driving taxi Elon Musk has announced that Tesla will wind down production of its Cybertruck, marking the end of…

2d ago ·theguardian.com

MIRA: Mitigating Pole Geometry Bias in Recurrent Language Models

We show that the Transformer's recurrent successors --- such as selective state-space models (SSMs), Receptance Weighted Key Value (RWKV), and Retentive Network (RetNet) --- can be characterized as…

2d ago ·arxiv.org

SmartBloch-Agent: An Agentic Framework for Automated MRI Sequence Design and Optimization

Magnetic resonance imaging (MRI) pulse sequences organize radiofrequency excitation, gradient encoding, and signal acquisition, determining magnetization evolution and image formation.

2d ago ·arxiv.org

Typed-Centrality Grounding for Agentic GraphRAG: A Symbolic Approach for Agentic Reasoning

Knowledge Graphs (KGs) and Large Language Models (LLMs) represent two approaches for knowledge representation and reasoning over heterogeneous data. Recent research has explored their integration through Graph Retrieval-Augmented Generation (GraphRAG) systems, which use KGs to provide structured context to LLMs.

2d ago ·arxiv.org