Tag
An author describes how they solved scaling issues in a 200+ tool AI system by implementing predefined playbooks for tool sequences, improving reliability by avoiding model-improvised routes in multi-step executions.
This systematic literature review investigates autonomous UAV route planning for coverage maximization in environmental monitoring, analyzing 562 records and reporting preliminary findings on algorithmic families, metrics, and validation practices.
This paper presents LegalFarePlan, a reproducible framework for fare-transparent urban rail route planning under non-additive fare rules, implementing multiple algorithms including bounded exact label-setting and Pareto-frontier search. Evaluation on synthetic and semi-synthetic benchmarks shows significant fare reductions via legal exit-and-reentry operations.
AlphaTransit combines Monte Carlo Tree Search with neural policy-value networks to optimize bus route design by predicting downstream quality without simulator rollouts. It achieves significant service rate improvements on a Bloomington transit benchmark.
Amap officially released amap-lbs-skill, an open-source toolkit (MIT license) adapted for the OpenClaw platform, providing five types of map data services including POI search, route planning, and trip planning, enabling AI Agents to directly call real local geographic data in China and output visual map links.
This paper introduces TransitLM, a large-scale dataset of over 13 million transit route planning records from Chinese cities, enabling map-free route generation via LLMs trained directly on planning data.