Problem, Research Strategy, and Findings: The rise of large language models (LLMs) raises a key question for urban planning: which forms of professional planning knowledge can AI replicate, and which still require human judgment? Although AI tools are increasingly used in planning practice, there is still no systematic framework for testing whether they can reason with the contextual sensitivity, value awareness, and institutional literacy central to planning expertise.
arXiv:2508.01300v2 Announce Type: replace Abstract: AI planning provides agents the ability to act autonomously towards achieving a goal in a given environment. Recent advances in Large Language Mode...
The paper evaluates the planning abilities of large language model (LLM) agents by comparing their performance against formal semantics defined in hidden PDDL models. Across five domains, four LLMs, six prompting strategies, and three agent architectures, the best setup solved 78% of solvable tasks offline but only 40% online, with limited recognition of unsolvable tasks and no clear benefit from more elaborate prompting. The study concludes that claims of LLM planning competence require validated action traces rather than end‑to‑end success rates.
arXiv:2606. 03685v1 Announce Type: cross Abstract: Supervised fine-tuning (SFT) improves end-to-end classical planning in large language models (LLMs), but do these models also learn to represent and reason about the planning problems they are solving?
GRASP is a multi-stage planning framework that improves the reliability of large language models on complex tasks. It separates planning into three specialized modules—GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation—allowing context isolation and strict macro-regularization. Experiments show GRASP outperforms direct LLM planners by significant margins on datasets such as Natural Plan Calendar Scheduling, ZebraLogic, and SciBench Math, and it mitigates performance collapse in multi-task and dual-task settings.
The article presents a minimal working model for large language model (LLM) systems, emphasizing four key distinctions—pretraining vs. deployment, distribution vs. samples, types of memory, and task competence vs. agency. Using this framework, it diagnoses six common misconceptions about LLMs (next‑token prediction, regression to the mean, training‑data regurgitation, model memory, alignment, and understanding), explaining what each misconception captures correctly, where it conflates distinctions, and the implications for evaluation, design, and governance. The model is applied to AI policy language, illustrating how policy can misrepresent these distinctions and offering a diagnostic toolkit to correct such errors.
PIE-APT introduces a unified framework for abductive planning over Temporal Dynamic Knowledge Graphs (TDKGs) using two modules: PIE-Abducer, which performs incremental direct-derivation abduction, and PIE-APT, which interleaves backward‑chaining A* search with PIE-Abducer to generate action sequences and abductive assumptions. The approach operates natively on the expressive SROIQ Description Logic, leveraging an incremental reasoner to maintain decidability and bypass the Ramification Problem. Evaluation on four OWL benchmarks demonstrates qualitative superiority over classical planners and shows that the direct‑derivation method outperforms a Minimal Hitting Set baseline in abductive enrichment.
arXiv:2606. 27757v1 Announce Type: new Abstract: Large language models (LLMs) have attracted widespread attention from academia and industry, yet their deployment raises critical security concerns regarding robustness and reliability.
GRASP is a multi-stage planning framework that separates planning into specialized modules: GenPlan for global macro-guidelines, RevPlan for exploring localized strategies, and VerPlan for multi-criteria evaluation. This strategy-aware approach yields state‑of‑the‑art accuracy on diverse datasets, outperforming direct LLM planners by up to 30.8% on ZebraLogic and reducing multi‑task degradation. GRASP’s context isolation and macro‑regularization also give it a 14.5% edge over frontier reasoning models like GPT‑5‑mini.
arXiv:2608. 16637v1 Announce Type: new Abstract: LLMs remain unreliable for long-horizon planning, often generating logically inconsistent or non-applicable plans.
PermitGPT is a generative‑AI framework that transforms unstructured construction permit descriptions into structured outputs for safety hazard identification, permit requirement specification, and community impact assessment. It aligns data from the NYC Department of Buildings, OSHA, and NYC 311 to create 90,000 prompt‑response pairs, fine‑tunes three open‑weight language models, and evaluates them on 2,833 test cases, reporting complementary performance across inference speed, lexical overlap, and semantic alignment. The study presents an initial AI‑assisted approach to construction governance and outlines future evaluation and validation directions.
Urban diagnosis integrates heterogeneous observations to identify urban problems, localize affected areas, and investigate contributing factors, informing evidence-based urban planning and management....
arXiv:2606. 17459v1 Announce Type: new Abstract: Evaluating the decision-making capabilities of large language models (LLMs) is a growing research priority, yet existing benchmarks focus on isolated cognitive tasks such as reasoning, knowledge retrieval, and economic rationality in stylized settings.