UrbanWell: Benchmarking Multimodal Large Language Models for Spatio-Temporal Urban Wellbeing Analytics

Understanding urban wellbeing from multimodal data requires integrating heterogeneous spatial and temporal signals, posing significant challenges for current multimodal large language models (MLLMs). We introduce UrbanWell, a large-scale benchmark designed to systematically evaluate the spatio-temporal reasoning capabilities of MLLMs for urban wellbeing analytics through joint modeling of satellite and street view imagery. UrbanWell spans 38 cities across multiple years and includes diverse indicators covering (1) environmental conditions (CO$_2$, NO$_2$, PM${2.5}$, and Normalized Difference Vegetation Index), (2) spatial accessibility (minimum distance to supermarkets and restaurants), (3) urban form (road length, road density, and land use), (4) urban vitality (population, economic activity diversity, and land use diversity), and (5) subjective perception attributes (e.g., safety, beauty, liveliness, wealth, and quietness). All indicators are aligned at grid level to enable standardized evaluation. Beyond static prediction, UrbanWell defines temporal reasoning tasks, including future value forecasting from historical observations and temporal trend classification. We benchmark 15 state-of-the-art representative MLLMs in a zero-shot setting, providing a comprehensive comparative evaluation across spatial and temporal dimensions. Experimental results indicate that while MLLMs capture salient spatial and perceptual cues, their performance varies substantially across heterogeneous urban indicators spanning environment and subjective perception. UrbanWell serves as a unified benchmark for evaluating multimodal spatial and temporal reasoning in urban wellbeing analytics, offering a standardized testbed for systematic assessment and future research on multimodal urban intelligence. Our codes and datasets are accessible via https://github.com/axin1301/UrbanWell-Benchmark.

Fundamentals of NOMA in Low-Earth Orbit Coordinated Multi-Satellite Networks

Coordinated multi-satellite (CoMS) transmission and non-orthogonal multiple access (NOMA) are envisioned to jointly enhance coverage, capacity, and spectrum efficiency for satellite networks. Their integration into a unified CoMS-NOMA framework will allow more efficient, reliable, and energy-efficient multi-user access. This paper investigates the downlink performance of CoMS-NOMA networks from a system-level perspective, in which multiple satellites cooperatively serve multiple users via NOMA. Leveraging tools from stochastic geometry, related angles and distances in CoMS-NOMA are first derived as intermediate results. Then, we obtain the combined signal power distributions and analyze coverage and spectrum performance under both inter- and intra-satellite interference, accounting for potential imperfect successive interference cancellation (SIC). The analytical model is validated across a range of system parameters, including the number of satellites, service region angle, error-propagation factor, and power allocation coefficients. Numerical results indicate that increasing the number of cooperative satellites does not always improve coverage and spectrum efficiency. Additionally, while a higher main-lobe gain improves coverage, a near-perfect SIC provides only slightly greater benefits than a reasonably good SIC. With properly selected power allocation coefficients, CoMS-NOMA achieves up to a 270% improvement in coverage and a 56% gain in sum spectral efficiency, compared with conventional orthogonal and single-satellite schemes, indicating potential for green, energy-efficient satellite networking.

DynaOD: Dynamic Origin-Destination Flow Generation with Discrete-to-Continuous Temporal Semantic Modeling

Dynamic origin-destination (OD) flow generation seeks to synthesize realistic mobility dynamics from temporal context alone, without relying on historical OD observations. A key challenge is to translate semantic temporal signals into temporally coherent OD patterns while preserving the inherent spatial heterogeneity of urban regions. We propose DynaOD, a semantic-driven framework that models temporal dynamics through two complementary perspectives: discrete directional trends that characterize qualitative shifts in urban activity patterns, and continuous temporal evolution that captures how such shifts unfold over time. By jointly encoding these temporal semantics, the framework constructs time-varying region representations that condition pretrained static OD generators in a lightweight and plug-and-play fashion. This modular design further supports scalable deployment and cross-city transferability. Extensive experiments on large-scale real-world datasets show that our method consistently outperforms representative baselines in both predictive accuracy and distributional fidelity. Code is publicly available at https://github.com/csjiezhao/DynaOD.

SlimSearcher: Training Efficiency-Aware Web Agents via Adaptive Reward Gating

Deep research agents have demonstrated remarkable capabilities in complex information-seeking tasks, yet this power comes at a steep computational cost. Driven by accuracy-focused training paradigms, current models adopt brute-force strategies characterized by blind tool dependency and performative reasoning-generating long, redundant trajectories that are far from necessary for resolving these tasks, leading to wasteful tool calls and excessive token consumption. To overcome this efficiency trap, we propose SlimSearcher, a principled framework that pushes the Pareto frontier between accuracy and computational cost across both Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL). In the SFT stage, SlimSearcher employs Pareto-efficient filtration to distill trajectories that are both successful and economical, guiding the model toward inherently efficiency-aware search behaviors. During RL, we introduce Adaptive Reward Gating, a dynamic reward-shaping mechanism that evaluates relative tool and token efficiency within a sampled cohort. By cascading these adaptive efficiency metrics with a strict correctness gate, our approach effectively avoids the brevity bias associated with absolute penalties and mitigates reward hacking. Extensive experiments on long-horizon benchmarks, including GAIA, BrowseComp, and XBenchDeepSearch, demonstrate that SlimSearcher reduces average tool-call rounds by 17%-58% while maintaining or improving accuracy.

SpatialAct: Probing Spatial Reasoning-to-Action Capabilities of VLM Agents in 3D Scenes

Humans can effortlessly perceive spatial layouts, form cognitive representations, reason about spatial relations, and translate such reasoning into actions in everyday 3D environments. Although recent vision-language models (VLMs) have shown promising performance on observation-conditioned spatial perception and reasoning tasks, it remains unclear whether they can build coherent spatial understanding, act upon it, and refine their actions through multi-turn feedback. To study this problem, we introduce \textbf{SpatialAct}, a simulator-grounded benchmark for probing \textit{action-conditioned spatial reasoning} in 3D scenes. Starting from the most challenging setting, Multi-turn Interactive Refinement, we further design its decomposed counterpart, Single-step Error Detection and Fix, together with five fundamental spatial ability tasks to diagnose the underlying causes of model failures. Experiments reveal a clear reasoning-to-action gap: current VLMs can perform well on isolated spatial reasoning tasks, but struggle to maintain coherent spatial beliefs and produce reliable actions during multi-turn feedback, substantially underperforming humans. These results suggest that current VLM agents still lack robust spatial state tracking under action-induced environment changes, even when low-level control is abstracted away.

LMM-Track4D: Eliciting 4D Dynamic Reasoning in LMMs via Trajectory-Grounded Dialogue

Recent large multimodal models (LMMs) have become increasingly capable on image and video understanding, yet still struggle to sustain 4D continuous spatiotemporal dynamic reasoning. To study this capability gap, we formulate trajectory-grounded multi-turn spatiotemporal dialogue, a new task in which a model must answer spatiotemporal queries while returning structured 3D target trajectories over an entire short clip or a specified segment of a longer clip, and introduce Track4D-Bench, a benchmark with 526 clip-level dialogue samples spanning 23.5k frames and 7.5k object annotations, for training and evaluation. Building on this task, we propose LMM-Track4D, which combines RTGE (Ray--Time Geometry Encoding), a dedicated streaming state token TRK for long-horizon dynamic propagation, and an Object-Slot Kinematic, Residual-Anchor (OSK-RA) decoder for stable 4-step 3D state estimation under occlusion and viewpoint variation. Experiments on Track4D-Bench show consistent improvements over strong baselines, suggesting that explicit dynamic state modeling is a useful design principle for eliciting 4D dynamic reasoning in LMMs. Our code and dataset will be publicly available at https://github.com/mikubaka88/LMM-Track4D.

Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning

Scaling critic capacity is a promising direction for enhancing off-policy reinforcement learning (RL). However, larger critics are prone to overfitting and unstable in replay-buffer-based bootstrap training. This paper leverages Low-Rank Adaptation (LoRA) as a structural-sparsity regularizer for off-policy critics. Our approach freezes randomly initialized base matrices and solely optimizes low-rank adapters, thereby constraining critic updates to a low-dimensional subspace. Built on top of SimbaV2, we further develop a LoRA formulation, compatible with SimbaV2, that preserves its hyperspherical normalization geometry under frozen-backbone training. We evaluate our method with SAC and FastTD3 on DeepMind Control locomotion and IsaacLab robotics benchmarks. LoRA consistently achieves lower critic loss during training and stronger policy performance. Extensive experiments demonstrate that adaptive low-rank updates provide a simple, scalable, and effective structural regularization for critic learning in off-policy RL.

ARMove: Learning to Predict Human Mobility through Agentic Reasoning

Human mobility prediction is a critical task but remains challenging due to its complexity and variability across populations and regions. Recently, large language models (LLMs) have made progress in zero-shot prediction, but existing methods suffer from limited interpretability (due to black-box reasoning), lack of iterative learning from new data, and poor transferability. In this paper, we introduce \textbf{ARMove}, a fully transferable framework for predicting human mobility through agentic reasoning. To address these limitations, ARMove employs standardized feature management with iterative optimization and user-specific customization: four major feature pools for foundational knowledge, user profiles for segmentation, and an automated generation mechanism integrating LLM knowledge. Robust generalization is achieved via agentic decision-making that adjusts feature weights to maximize accuracy while providing interpretable decision paths. Finally, large-small model synergy distills strategies from large LLMs (e.g., 72B) to smaller ones (e.g., 7B), reducing costs and enhancing performance ceilings. Extensive experiments on four global datasets show ARMove outperforms state-of-the-art baselines on 6 out of 12 metrics (gains of 0.78\% to 10.47\%), with transferability tests confirming robustness across regions, users, and scales. The other 4 items also achieved suboptimal results. Transferability tests confirm its 19 robustness across regions, user groups, and model scales, while interpretability 20 analysis highlights its transparency in decision-making. Our codes are available at: https://anonymous.4open.science/r/ARMove-F847.

Enhancing Local Life Service Recommendation with Agentic Reasoning in Large Language Model

Local life service recommendation is distinct from general recommendation scenarios due to its strong living need-driven nature. Fundamentally, accurately identifying a user's immediate living need and recommending the corresponding service are inextricably linked tasks. However, prior works typically treat them in isolation, failing to achieve a unified modeling of need prediction and service recommendation. In this paper, we propose a novel large language model based framework that jointly performs living need prediction and service recommendation. To address the challenge of noise in raw consumption data, we introduce a behavioral clustering approach that filters out accidental factors and selectively preserves typical patterns. This enables the model to learn a robust logical basis for need generation and spontaneously generalize to long-tail scenarios. To navigate the vast search space stemming from diverse needs, merchants, and complex mapping paths, we employ a curriculum learning strategy combined with reinforcement learning with verifiable rewards. This approach guides the model to sequentially learn the logic from need generation to category mapping and specific service selection. Extensive experiments demonstrate that our unified framework significantly enhances both living need prediction performance and recommendation accuracy, validating the effectiveness of jointly modeling living needs and user behaviors.

Resonance4D: Frequency-Domain Motion Supervision for Preset-Free Physical Parameter Learning in 4D Dynamic Physical Scene Simulation

Physics-driven 4D dynamic simulation from static 3D scenes remains constrained by an overlooked contradiction: reliable motion supervision often relies on online video diffusion or optical-flow pipelines whose computational cost exceeds that of the simulator itself. Existing methods further simplify inverse physical modeling by optimizing only partial material parameters, limiting realism in scenes with complex materials and dynamics. We present Resonance4D, a physics-driven 4D dynamic simulation framework that couples 3D Gaussian Splatting with the Material Point Method through lightweight yet physically expressive supervision. Our key insight is that dynamic consistency can be enforced without dense temporal generation by jointly constraining motion in complementary domains. To this end, we introduce Dual-domain Motion Supervision (DMS), which combines spatial structural consistency for local deformation with frequency-domain spectral consistency for oscillatory and global dynamic patterns, substantially reducing training cost and memory overhead while preserving physically meaningful motion cues. To enable stable full-parameter physical recovery, we further combine zero-shot text-prompted segmentation with simulation-guided initialization to automatically decompose Gaussians into object-part-level regions and support joint optimization of full material parameters. Experiments on both synthetic and real scenes show that Resonance4D achieves strong physical fidelity and motion consistency while reducing peak GPU memory from over 35\,GB to around 20\,GB, enabling high-fidelity physics-driven 4D simulation on a single consumer-grade GPU.