arXiv subjects

Zhiheng Zheng

Publications and source records attributed to Zhiheng Zheng.

13 recordsLinked to original sources

arXiv2026

UrbanWorld2.0: A Multimodal Agentic Framework for Reality-Aligned 3D World Generation at City-Scale

The automated generation of high-fidelity, city-scale 3D environments remains a formidable challenge with profound academic and industrial implications. However, existing methods struggle to achieve the necessary quality, fidelity, and scalability. To address this, we propose UrbanWorld2.0, a reality-aligned intelligent multimodal synthesis engine that creates detailed, city-scale 3D worlds of high fidelity. We introduce an agentic framework that leverages diverse multimodal foundation tools to acquire real-world knowledge, maintain robust intermediate representations, and construct complex 3D scenes. This agentic design, featuring dynamic data processing, iterative self-reflection and refinement, and the invocation of advanced multimodal tools, minimizes cumulative errors and enhances overall performance. Extensive quantitative experiments and qualitative analyzes validate the superior performance of UrbanWorld2.0 in real-world alignment, shape precision, texture fidelity, and aesthetics level, achieving a win rate of over 86\% against existing baselines for overall perceptual quality. This combination of 3D quality, reality alignment, scalability, and seamless compatibility with computer graphics pipelines makes UrbanWorld2.0 a promising foundation for applications in immersive media, embodied intelligence, and world models.

cs.CV↗

arXiv2026

Hypergraphs without Subgraphs of Given Connectivity

In this paper, we study the problem of determining the maximum number $F_r(n,k)$ of edges in an $n$-vertex $r$-uniform hypergraph that contains no $(k+1)$-connected subgraph. The graph case, initiated by Mader, is a classical problem in graph theory that remains open. We first establish a limit theorem for $F_r(n,k)$ for all $k\ge r\ge 2$. As a consequence, we prove for the first time that, in Mader's problem (i.e., $r=2$), there exists a constant $c_k>0$ such that $F_2(n,k)=c_k n+O_k(1)$, and, for every $r\ge 3$, we determine $F_r(n,k)$ up to an $O(n)$ error term, thereby identifying its leading asymptotic term. We also address a related question of Carmesin by establishing a tight bound for $r$-uniform hypergraphs with no $(k+1)$-connected subgraph on more than $Ck$ vertices for any constant $C>2$ and sufficiently large $r$, and further obtain an asymptotically tight bound in the case $C=2$. Our proof combines the separator tree method introduced by Carmesin with several new combinatorial and optimization techniques, and we conclude with related remarks and open problems.

math.CO↗

arXiv2026

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.

cs.CV↗

arXiv2026

WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation

Aerial vision-language navigation (VLN) requires agents to follow natural-language instructions through closed-loop perception and action in 3D environments. We argue that aerial VLN can be formulated as a prediction-driven world-action problem: the agent should anticipate latent world evolution and act according to the predicted consequences. To this end, we propose WorldVLN, the first autoregressive world action model for aerial VLN. Unlike full-sequence video-generation world models that generate an entire visual clip, WorldVLN adapts a latent autoregressive video backbone to predict short-horizon world-state transitions and directly decodes them into executable waypoint actions. After each action segment is executed, newly received observations are encoded back into the autoregressive context, enabling closed-loop world-action prediction. We further introduce a two-stage training framework that first grounds the video prior in instruction-conditioned navigation dynamics and then develops Action-aware GRPO, the first reinforcement learning method tailored to autoregressive WAMs, to optimize waypoint decisions through their downstream rollout consequences. On public outdoor and indoor benchmarks, WorldVLN consistently outperforms existing Vision-Language-Action baselines with 12\%+ success-rate gains and larger advantages on challenging cases. It further transfers zero-shot to real drone deployment, suggesting that the proposed WorldVLN offers a promising route for spatial action tasks. Demos and code are available at https://embodiedcity.github.io/WorldVLN/.

cs.RO↗

arXiv2026

On Spielman's Laplacian Eigenratio Conjecture and Related Problems

Let $G$ be an $n$-vertex graph with Laplacian eigenvalues $0=λ_1(G)\le λ_2(G)\le\cdots\le λ_n(G)$. Motivated by the Alon-Boppana bound and the Ramanujan phenomenon for regular graphs, Spielman conjectured that, for every graph $G$ with fixed average degree $d\ge 1$, its Laplacian eigenratio satisfies $$ \frac{λ_2(G)}{λ_n(G)} \le \frac{d-2\sqrt{d-1}}{d+2\sqrt{d-1}}+o_n(1), $$ where $o_n(1)\to 0$ as $n\to\infty$. The main purpose of this paper is to investigate this conjecture. We show that the situation is mixed. On the negative side, the conjecture fails for infinitely many average degrees $d>2$, via constructions based on bipartite Ramanujan graphs. On the positive side, it holds in two important settings: we verify it for all average degrees $d\le 2$, and we prove it for all regular graphs. In fact, for regular graphs we obtain stronger bounds comparing higher Laplacian eigenvalues. As a consequence, we show that for every fixed $d\ge 3$ and every $\varepsilon>0$, every sufficiently large $d$-regular Ramanujan graph has linearly many adjacency eigenvalues below $-2\sqrt{d-1}+\varepsilon$, thereby strengthening earlier results of Li and Cioabă by giving an unconditional result of this form. We also settle two related conjectures: one of You and Liu concerning the maximum Laplacian eigenratio of trees, and one of Gu concerning the Hamiltonicity of graphs with large Laplacian eigenratio.

math.CO↗

arXiv2026

AgentSociety: Large-Scale Simulation of LLM-Driven Generative Agents Advances Understanding of Human Behaviors and Society

Understanding human behavior and society is a central focus in social sciences, with the rise of generative social science marking a significant paradigmatic shift. By leveraging bottom-up simulations, it replaces costly and logistically challenging traditional experiments with scalable, replicable, and systematic computational approaches for studying complex social dynamics. Recent advances in large language models (LLMs) have further transformed this research paradigm, enabling the creation of human-like generative social agents and realistic simulacra of society. In this paper, we propose AgentSociety, a large-scale social simulator that integrates LLM-driven agents, a realistic societal environment, and a powerful large-scale simulation engine. Based on the proposed simulator, we generate social lives for over 10k agents, simulating their 5 million interactions both among agents and between agents and their environment. Furthermore, we explore the potential of AgentSociety as a testbed for computational social experiments, focusing on five key social issues: polarization, the spread of inflammatory messages, the effects of universal basic income policies, the impact of external shocks such as hurricanes, and urban sustainability. These five issues serve as valuable cases for assessing AgentSociety's support for typical research methods -- such as surveys, interviews, and interventions -- as well as for investigating the patterns, causes, and underlying mechanisms of social issues. The alignment between AgentSociety's outcomes and real-world experimental results not only demonstrates its ability to capture human behaviors and their underlying mechanisms, but also underscores its potential as an important platform for social scientists and policymakers.

cs.SI↗

arXiv2025

On the multicolor Turán conjecture for color-critical graphs

A {\it simple $k$-coloring} of a multigraph $G$ is a decomposition of the edge multiset as a disjoint sum of $k$ simple graphs which are referred as colors. A subgraph $H$ of a multigraph $G$ is called {\it multicolored} if its edges receive distinct colors in a given simple $k$-coloring of $G$. In 2004, Keevash-Saks-Sudakov-Verstraëte introduced the {\it $k$-color Turán number} $ex_k(n,H)$, which denotes the maximum number of edges in an $n$-vertex multigraph that has a simple $k$-coloring containing no multicolored copies of $H$. They made a conjecture for any $r\geq 3$ and $r$-color-critical graph $H$ that in the range of $k\geq \frac{r-1}{r-2}(e(H)-1)$, if $n$ is sufficiently large, then $ex_k(n, H)$ is achieved by the multigraph consisting of $k$ colors all of which are identical copies of the Turán graph $T_{r-1}(n)$. In this paper, we show that this holds in the range of $k\geq 2\frac{r-1}{r}(e(H)-1)$, significantly improving earlier results. Our proof combines the stability argument of Chakraborti-Kim-Lee-Liu-Seo with a novel graph packing technique for embedding multigraphs.

math.CO↗

arXiv2025

CityEQA: A Hierarchical LLM Agent on Embodied Question Answering Benchmark in City Space

Embodied Question Answering (EQA) has primarily focused on indoor environments, leaving the complexities of urban settings-spanning environment, action, and perception-largely unexplored. To bridge this gap, we introduce CityEQA, a new task where an embodied agent answers open-vocabulary questions through active exploration in dynamic city spaces. To support this task, we present CityEQA-EC, the first benchmark dataset featuring 1,412 human-annotated tasks across six categories, grounded in a realistic 3D urban simulator. Moreover, we propose Planner-Manager-Actor (PMA), a novel agent tailored for CityEQA. PMA enables long-horizon planning and hierarchical task execution: the Planner breaks down the question answering into sub-tasks, the Manager maintains an object-centric cognitive map for spatial reasoning during the process control, and the specialized Actors handle navigation, exploration, and collection sub-tasks. Experiments demonstrate that PMA achieves 60.7% of human-level answering accuracy, significantly outperforming competitive baselines. While promising, the performance gap compared to humans highlights the need for enhanced visual reasoning in CityEQA. This work paves the way for future advancements in urban spatial intelligence. Dataset and code are available at https://github.com/BiluYong/CityEQA.git.

cs.AI↗

arXiv2025

AgentSociety Challenge: Designing LLM Agents for User Modeling and Recommendation on Web Platforms

The AgentSociety Challenge is the first competition in the Web Conference that aims to explore the potential of Large Language Model (LLM) agents in modeling user behavior and enhancing recommender systems on web platforms. The Challenge consists of two tracks: the User Modeling Track and the Recommendation Track. Participants are tasked to utilize a combined dataset from Yelp, Amazon, and Goodreads, along with an interactive environment simulator, to develop innovative LLM agents. The Challenge has attracted 295 teams across the globe and received over 1,400 submissions in total over the course of 37 official competition days. The participants have achieved 21.9% and 20.3% performance improvement for Track 1 and Track 2 in the Development Phase, and 9.1% and 15.9% in the Final Phase, representing a significant accomplishment. This paper discusses the detailed designs of the Challenge, analyzes the outcomes, and highlights the most successful LLM agent designs. To support further research and development, we have open-sourced the benchmark environment at https://tsinghua-fib-lab.github.io/AgentSocietyChallenge.

cs.IR↗

arXiv2024

EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment

Embodied artificial intelligence emphasizes the role of an agent's body in generating human-like behaviors. The recent efforts on EmbodiedAI pay a lot of attention to building up machine learning models to possess perceiving, planning, and acting abilities, thereby enabling real-time interaction with the world. However, most works focus on bounded indoor environments, such as navigation in a room or manipulating a device, with limited exploration of embodying the agents in open-world scenarios. That is, embodied intelligence in the open and outdoor environment is less explored, for which one potential reason is the lack of high-quality simulators, benchmarks, and datasets. To address it, in this paper, we construct a benchmark platform for embodied intelligence evaluation in real-world city environments. Specifically, we first construct a highly realistic 3D simulation environment based on the real buildings, roads, and other elements in a real city. In this environment, we combine historically collected data and simulation algorithms to conduct simulations of pedestrian and vehicle flows with high fidelity. Further, we designed a set of evaluation tasks covering different EmbodiedAI abilities. Moreover, we provide a complete set of input and output interfaces for access, enabling embodied agents to easily take task requirements and current environmental observations as input and then make decisions and obtain performance evaluations. On the one hand, it expands the capability of existing embodied intelligence to higher levels. On the other hand, it has a higher practical value in the real world and can support more potential applications for artificial general intelligence. Based on this platform, we evaluate some popular large language models for embodied intelligence capabilities of different dimensions and difficulties.

cs.AI↗

arXiv2024

OpenCity: A Scalable Platform to Simulate Urban Activities with Massive LLM Agents

Agent-based models (ABMs) have long been employed to explore how individual behaviors aggregate into complex societal phenomena in urban space. Unlike black-box predictive models, ABMs excel at explaining the micro-macro linkages that drive such emergent behaviors. The recent rise of Large Language Models (LLMs) has led to the development of LLM agents capable of simulating urban activities with unprecedented realism. However, the extreme high computational cost of LLMs presents significant challenges for scaling up the simulations of LLM agents. To address this problem, we propose OpenCity, a scalable simulation platform optimized for both system and prompt efficiencies. Specifically, we propose a LLM request scheduler to reduce communication overhead by parallelizing requests through IO multiplexing. Besides, we deisgn a "group-and-distill" prompt optimization strategy minimizes redundancy by clustering agents with similar static attributes. Through experiments on six global cities, OpenCity achieves a 600-fold acceleration in simulation time per agent, a 70% reduction in LLM requests, and a 50% reduction in token usage. These improvements enable the simulation of 10,000 agents' daily activities in 1 hour on commodity hardware. Besides, the substantial speedup of OpenCity allows us to establish a urban simulation benchmark for LLM agents for the first time, comparing simulated urban activities with real-world data in 6 major cities around the globe. We believe our OpenCity platform provides a critical infrastructure to harness the power of LLMs for interdisciplinary studies in urban space, fostering the collective efforts of broader research communities. Code repo is available at https://anonymous.4open.science/r/Anonymous-OpenCity-42BD.

cs.MA↗

arXiv2021

Rotation-induced significant modulation of near-field radiative heat transfer between hyperbolic nanoparticles

Modulation of near-field radiative heat transfer (NFRHT) with rotated anisotropic hBN and MoO3 nanoparticles (NPs) are investigated. The spectral heat power, total heat power and electric field energy density are calculated at different particle orientations. Numerical results show that the modulation factor of the MoO3 NPs could be up to ~12000 with particle radius of 40 nm at a gap distance of 200 nm, which is ~ 10-fold larger than the state of the art. Excitation of localized hyperbolic phonon polaritons (LHPPs) in different particle orientations allow for the excellent modulation. The modulation factor of the hBN NPs is 5.9 due to the insensitivity of the LHPPs in the type II hyperbolic band to the particle orientations. This work not only provides a new method to modulate NFRHT in particle systems, but also paves the way to explore radiative heat transfer characteristics of anisotropic media.

physics.optics↗

arXiv2018

Re-estimation of thermal contact resistance considering near-field thermal radiation effect

Thermal contact has always been a hot issue in many engineering fields and thermal contact resistance (TCR) is one of the important indicators weighing the heat transfer efficiency among the interfaces. In this paper, the contact heat transfer of conforming rough surfaces is theoretically re-estimated considering both the heat transfer from contact and non-contact regions. The fluctuational electrodynamics (an ab initio calculation) is adopted to calculate the thermal radiation. The contribution of contact regions is estimated by the CMY TCR model and further studied by modelling specific surfaces with corresponding surface roughness power spectrum (PSD). Several tests are presented where aluminum and amorphous alumina are mainly used in the simulations. Studies showed that there exists a significant synergy between the thermal conduction and near-field thermal radiation at the interface in a certain range of effective roughness. When the effective roughness is near to the scales of submicron, the near-field radiation effect should not be neglected even at room temperature.

physics.app-ph↗