Reasoning Is All You Need for Urban Planning AI

AI has proven highly successful at urban planning analysis -- learning patterns from data to predict future conditions. The next frontier is AI-assisted decision-making: agents that recommend sites, allocate resources, and evaluate trade-offs while reasoning transparently about constraints and stakeholder values. Recent breakthroughs in reasoning AI -- CoT prompting, ReAct, and multi-agent collaboration frameworks -- now make this vision achievable. This position paper presents the Agentic Urban Planning AI Framework for reasoning-capable planning agents that integrates three cognitive layers (Perception, Foundation, Reasoning) with six logic components (Analysis, Generation, Verification, Evaluation, Collaboration, Decision) through a multi-agents collaboration framework. We demonstrate why planning decisions require explicit reasoning capabilities that are value-based (applying normative principles), rule-grounded (guaranteeing constraint satisfaction), and explainable (generating transparent justifications) -- requirements that statistical learning alone cannot fulfill. We compare reasoning agents with statistical learning, present a comprehensive architecture with benchmark evaluation metrics, and outline critical research challenges. This framework shows how AI agents can augment human planners by systematically exploring solution spaces, verifying regulatory compliance, and deliberating over trade-offs transparently -- not replacing human judgment but amplifying it with computational reasoning capabilities.

LLM-as-a-Judge: Toward World Models for Slate Recommendation Systems

Modeling user preferences across domains remains a key challenge in slate recommendation (i.e. recommending an ordered sequence of items) research. We investigate how Large Language Models (LLM) can effectively act as world models of user preferences through pairwise reasoning over slates. We conduct an empirical study involving several LLMs on three tasks spanning different datasets. Our results reveal relationships between task performance and properties of the preference function captured by LLMs, hinting towards areas for improvement and highlighting the potential of LLMs as world models in recommender systems.

Investigating U.S. Consumer Demand for Food Products with Innovative Transportation Certificates Based on Stated Preferences and Machine Learning Approaches

This paper utilizes a machine learning model to estimate the consumer's behavior for food products with innovative transportation certificates in the U.S. Building on previous research that examined demand for food products with supply chain traceability using stated preference analysis, transportation factors were identified as significant in consumer food purchasing choices. Consequently, a second experiment was conducted to pinpoint the specific transportation attributes valued by consumers. A machine learning model was applied, and five innovative certificates related to transportation were proposed: Transportation Mode, Internet of Things (IoT), Safety measures, Energy Source, and Must Arrive By Dates (MABDs). The preference experiment also incorporated product-specific and decision-maker factors for control purposes. The findings reveal a notable inclination toward safety and energy certificates within the transportation domain of the U.S. food supply chain. Additionally, the study examined the influence of price, product type, certificates, and decision-maker factors on purchasing choices. Ultimately, the study offers data-driven recommendations for improving food supply chain systems.

High-Resolution Forest Mapping from L-Band Interferometric SAR Time Series using Deep Learning over Northern Spain

In this study, we examine the potential of high-resolution forest mapping using L-band interferometric time series datasets and deep learning modeling. Our SAR data are represented by a time series of nine ALOS-2 PALSAR-2 dual-pol SAR images acquired at near-zero spatial baseline over a study site in Asturias, Northern Spain. Reference data are collected using airborne laser scanning. We examine the performance of several candidate deep learning models from UNet-family with various combinations of input polarimetric and interferometric features. In addition to basic Vanilla UNet, attention reinforced UNet model with squeeze-excitation blocks (SeU-Net) and advanced UNet model with nested structure and skip pathways are used. Studied features include dual pol interferometric observables additionally incorporating model-based derived measures. Results show that adding model-based inverted InSAR features or InSAR coherence layers improves retrieval accuracy compared to using backscatter intensity only. Use of attention mechanisms and nested connection fusion provides better predictions than using Vanilla UNet or traditional machine learning methods. Forest height retrieval accuracies range between 3.1-3.8 m (R2 = 0.45--0.55) at 20 m resolution when only intensity data are used, and improve to less than 2.8 m when both intensity and interferometric coherence features are included. At 40 m and 60 m resolution, retrieval performance further improves, primarily due to higher SNR in both the intensity and interferometric layers. When using intensity at 60 m resolution, best achieved RMSE is 2.2 m, while when using all suitable input features the achieved error is 1.95 m. We recommend this hybrid approach for L-band SAR retrievals also suitable for NISAR and future ROSE-L missions.

RxSafeBench: Identifying Medication Safety Issues of Large Language Models in Simulated Consultation

Numerous medical systems powered by Large Language Models (LLMs) have achieved remarkable progress in diverse healthcare tasks. However, research on their medication safety remains limited due to the lack of real world datasets, constrained by privacy and accessibility issues. Moreover, evaluation of LLMs in realistic clinical consultation settings, particularly regarding medication safety, is still underexplored. To address these gaps, we propose a framework that simulates and evaluates clinical consultations to systematically assess the medication safety capabilities of LLMs. Within this framework, we generate inquiry diagnosis dialogues with embedded medication risks and construct a dedicated medication safety database, RxRisk DB, containing 6,725 contraindications, 28,781 drug interactions, and 14,906 indication-drug pairs. A two-stage filtering strategy ensures clinical realism and professional quality, resulting in the benchmark RxSafeBench with 2,443 high-quality consultation scenarios. We evaluate leading open-source and proprietary LLMs using structured multiple choice questions that test their ability to recommend safe medications under simulated patient contexts. Results show that current LLMs struggle to integrate contraindication and interaction knowledge, especially when risks are implied rather than explicit. Our findings highlight key challenges in ensuring medication safety in LLM-based systems and provide insights into improving reliability through better prompting and task-specific tuning. RxSafeBench offers the first comprehensive benchmark for evaluating medication safety in LLMs, advancing safer and more trustworthy AI-driven clinical decision support.

Watermarking Large Language Models in Europe: Interpreting the AI Act in Light of Technology

To foster trustworthy Artificial Intelligence (AI) within the European Union, the AI Act requires providers to mark and detect the outputs of their general-purpose models. The Article 50 and Recital 133 call for marking methods that are ''sufficiently reliable, interoperable, effective and robust''. Yet, the rapidly evolving and heterogeneous landscape of watermarks for Large Language Models (LLMs) makes it difficult to determine how these four standards can be translated into concrete and measurable evaluations. Our paper addresses this challenge, anchoring the normativity of European requirements in the multiplicity of watermarking techniques. Introducing clear and distinct concepts on LLM watermarking, our contribution is threefold. (1) Watermarking Categorisation: We propose an accessible taxonomy of watermarking methods according to the stage of the LLM lifecycle at which they are applied - before, during, or after training, and during next-token distribution or sampling. (2) Watermarking Evaluation: We interpret the EU AI Act's requirements by mapping each criterion with state-of-the-art evaluations on robustness and detectability of the watermark, and of quality of the LLM. Since interoperability remains largely untheorised in LLM watermarking research, we propose three normative dimensions to frame its assessment. (3) Watermarking Comparison: We compare current watermarking methods for LLMs against the operationalised European criteria and show that no approach yet satisfies all four standards. Encouraged by emerging empirical tests, we recommend further research into watermarking directly embedded within the low-level architecture of LLMs.

DQN Performance with Epsilon Greedy Policies and Prioritized Experience Replay

We present a detailed study of Deep Q-Networks in finite environments, emphasizing the impact of epsilon-greedy exploration schedules and prioritized experience replay. Through systematic experimentation, we evaluate how variations in epsilon decay schedules affect learning efficiency, convergence behavior, and reward optimization. We investigate how prioritized experience replay leads to faster convergence and higher returns and show empirical results comparing uniform, no replay, and prioritized strategies across multiple simulations. Our findings illuminate the trade-offs and interactions between exploration strategies and memory management in DQN training, offering practical recommendations for robust reinforcement learning in resource-constrained settings.

Inter-Agent Trust Models: A Comparative Study of Brief, Claim, Proof, Stake, Reputation and Constraint in Agentic Web Protocol Design-A2A, AP2, ERC-8004, and Beyond

As the "agentic web" takes shape-billions of AI agents (often LLM-powered) autonomously transacting and collaborating-trust shifts from human oversight to protocol design. In 2025, several inter-agent protocols crystallized this shift, including Google's Agent-to-Agent (A2A), Agent Payments Protocol (AP2), and Ethereum's ERC-8004 "Trustless Agents," yet their underlying trust assumptions remain under-examined. This paper presents a comparative study of trust models in inter-agent protocol design: Brief (self- or third-party verifiable claims), Claim (self-proclaimed capabilities and identity, e.g. AgentCard), Proof (cryptographic verification, including zero-knowledge proofs and trusted execution environment attestations), Stake (bonded collateral with slashing and insurance), Reputation (crowd feedback and graph-based trust signals), and Constraint (sandboxing and capability bounding). For each, we analyze assumptions, attack surfaces, and design trade-offs, with particular emphasis on LLM-specific fragilities-prompt injection, sycophancy/nudge-susceptibility, hallucination, deception, and misalignment-that render purely reputational or claim-only approaches brittle. Our findings indicate no single mechanism suffices. We argue for trustless-by-default architectures anchored in Proof and Stake to gate high-impact actions, augmented by Brief for identity and discovery and Reputation overlays for flexibility and social signals. We comparatively evaluate A2A, AP2, ERC-8004 and related historical variations in academic research under metrics spanning security, privacy, latency/cost, and social robustness (Sybil/collusion/whitewashing resistance). We conclude with hybrid trust model recommendations that mitigate reputation gaming and misinformed LLM behavior, and we distill actionable design guidelines for safer, interoperable, and scalable agent economies.

A Survey on Generative Recommendation: Data, Model, and Tasks

Recommender systems serve as foundational infrastructure in modern information ecosystems, helping users navigate digital content and discover items aligned with their preferences. At their core, recommender systems address a fundamental problem: matching users with items. Over the past decades, the field has experienced successive paradigm shifts, from collaborative filtering and matrix factorization in the machine learning era to neural architectures in the deep learning era. Recently, the emergence of generative models, especially large language models (LLMs) and diffusion models, have sparked a new paradigm: generative recommendation, which reconceptualizes recommendation as a generation task rather than discriminative scoring. This survey provides a comprehensive examination through a unified tripartite framework spanning data, model, and task dimensions. Rather than simply categorizing works, we systematically decompose approaches into operational stages-data augmentation and unification, model alignment and training, task formulation and execution. At the data level, generative models enable knowledge-infused augmentation and agent-based simulation while unifying heterogeneous signals. At the model level, we taxonomize LLM-based methods, large recommendation models, and diffusion approaches, analyzing their alignment mechanisms and innovations. At the task level, we illuminate new capabilities including conversational interaction, explainable reasoning, and personalized content generation. We identify five key advantages: world knowledge integration, natural language understanding, reasoning capabilities, scaling laws, and creative generation. We critically examine challenges in benchmark design, model robustness, and deployment efficiency, while charting a roadmap toward intelligent recommendation assistants that fundamentally reshape human-information interaction.

Analytical Model of NR-V2X Mode 2 with Re-Evaluation Mechanism

Massive message transmissions, unpredictable aperiodic messages, and high-speed moving vehicles contribute to the complex wireless environment, resulting in inefficient resource collisions in Vehicle to Everything (V2X). In order to achieve better medium access control (MAC) layer performance, 3GPP introduced several new features in NR-V2X. One of the most important is the re-evaluation mechanism. It allows the vehicle to continuously sense resources before message transmission to avoid resource collisions. So far, only a few articles have studied the re-evaluation mechanism of NR-V2X, and they mainly focus on network simulator that do not consider variable traffic, which makes analysis and comparison difficult. In this paper, an analytical model of NR-V2X Mode 2 is established, and a message generator is constructed by using discrete time Markov chain (DTMC) to simulate the traffic pattern recommended by 3GPP advanced V2X services. Our study shows that the re-evaluation mechanism improves the reliability of NR-V2X transmission, but there are still local improvements needed to reduce latency.