Lin Chen

Cities thrive on social interactions that foster well-being, innovation, and prosperity; yet, exogenous shocks such as pandemics, hurricanes, and wildfires can severely disrupt them. Different urban venues exhibit widely divergent response patterns, raising key questions about what factors contribute to these differences and how we can anticipate and respond to them. Understanding these questions is crucial for safeguarding social resilience, the capacity of urban venues to maintain both visitation and diversity. In this study, we analyze large-scale human mobility data from 15 US cities covering more than 103 million residents across three distinct urban shocks. Despite a general trend of declining visitation and weakened social mixing (i.e., intensified segregation) during shocks, our analysis reveals 36.28%-53.01% of venues exhibit reduced segregation, and 21.04%-38.55% of venues exhibit increased visitation. By constructing a mobility network interlinking types of urban venues, we reveal that eigenvector network centrality tends to indicate the provision of essential services and robustly predicts social resilience across varied urban shocks. Specifically, centrality elevates the explanatory power by more than 80% in predicting both segregation and mobility change, compared with more intuitive features, including pre-shock segregation and mobility. Furthermore, while core venues (high centrality) and peripheral ones (low centrality) share a similar spatial distribution, they manifest distinct spatiotemporal visitation patterns, with core locations featuring shorter visit distances, broader neighborhood visitation, shorter visitor dwell times, and steadier popularity throughout the day. Such patterns imply a dual social mechanism, where core venues sustain neighborhood-level social ties through frequent informal interaction, while peripheral ones facilitate deeper engagement around specialized interests and their corresponding social circles. This suggests that crisis-response efforts should prioritize safeguarding core venue accessibility and their essential services to maintain everyday interaction, while directing targeted support to peripheral venues in order to restore specialized community and exchange following shocks. By bridging urban mobility research with economic theories that distinguish staple from discretionary products, we propose a well-and-pool analogy that suggests how people spend their varying urban mobility budgets. In crisis, citizens invest their limited mobility on essentials--like scarce water collecting in a deep well--but when mobility is abundant, like water after rain, people spread across many specialized venues, like water pooling across uneven ground. This operational analogy and our findings offer a new, broadly applicable lens on policymaking for urban social resilience and effective crisis response.

Reinforcement learning (RL), a pivotal machine learning paradigm, is becoming essential in the post-training of large language models (LLMs), enhancing their reasoning capabilities and alignment with human preferences. However, adapting conventional RL to LLMs introduces challenges stemming from their massive parameter size and the vast natural language action space. In this survey, we conduct a systematic literature review of RL in the era of LLMs. First, we provide a taxonomy of challenges faced in each stage of the RL training loop, including action exploration, trajectory collection, reward evaluation, and model update. We then introduce recently developed methods to address these issues, ranging from logical structure navigation, training data construction to reward design and advantage estimation. Afterward, we elaborate on the application of these techniques in diverse domains such as mathematics, coding, medicine, and information retrieval, analyzing how innovations in the RL pipeline enhance the domain-specific LLMs. Finally, we discuss the limitations and side effects of applying RL to LLMs and explore open problems and future directions like the balance between efficiency and effectiveness, and algorithm-system co-design. This survey helps researchers understand recent progress and inspire novel research to address current challenges and realize the full potential of RL for LLMs.

Recent advances in large language models (LLMs) have enabled the development of AI agents that exhibit increasingly human-like behaviors, including planning, adaptation, and social dynamics across diverse, interactive, and open-ended scenarios. These behaviors are not solely the product of the internal architectures of the underlying models, but emerge from their integration into agentic systems operating within specific contexts, where environmental factors, social cues, and interaction feedbacks shape behavior over time. This evolution necessitates a new scientific perspective: AI Agent Behavioral Science. Rather than focusing only on internal mechanisms, this perspective emphasizes the systematic observation of behavior, design of interventions to test hypotheses, and theory-guided interpretation of how AI agents act, adapt, and interact over time. We systematize a growing body of research across individual agent, multi-agent, and human-agent interaction settings, and further demonstrate how this perspective informs responsible AI by treating fairness, safety, interpretability, accountability, and privacy as behavioral properties. By unifying recent findings and laying out future directions, we position AI Agent Behavioral Science as a necessary complement to traditional model-centric approaches, providing essential tools for understanding, evaluating, and governing the real-world behavior of increasingly autonomous AI systems.

Understanding experienced segregation in urban daily life is crucial for addressing societal inequalities and fostering inclusivity. The abundance of user-generated reviews on social media encapsulates nuanced perceptions and feelings associated with different places, offering rich insights into segregation. However, leveraging this data poses significant challenges due to its vast volume, ambiguity, and confluence of diverse perspectives. To tackle these challenges, we propose a novel Large Language Model (LLM) Agent to automate online review mining for segregation prediction. Specifically, we propose a reflective LLM coder to digest social media content into insights consistent with real-world feedback, and eventually produce a codebook capturing key dimensions that signal segregation experience, such as cultural resonance and appeal, accessibility and convenience, and community engagement and local involvement. Guided by the codebook, LLMs can generate both informative review summaries and ratings for segregation prediction. Moreover, we design a REasoning-and-EMbedding (RE'EM) framework, which combines the reasoning and embedding capabilities of language models to integrate multi-channel features for segregation prediction. Experiments on real-world data demonstrate that our agent substantially improves prediction accuracy, with a 22.79% elevation in R^2 and a 9.33% reduction in MSE. The derived codebook is generalizable across three different cities, consistently improving prediction accuracy. Moreover, our user study confirms that the codebook-guided summaries provide cognitive gains for human participants in perceiving POIs' social inclusiveness. Our study marks an important step toward understanding implicit social barriers and inequalities, demonstrating the great potential of promoting social inclusiveness with Web technology.

The lived experience of urban life is shaped by personal mobility through dynamic relationships and resources, marked not only by access and opportunity, but also inequality and segregation. The recent availability of fine-grained mobility data and context attributes ranging from venue type to demographic mixture offer researchers a deeper understanding of experienced inequalities at scale, and pose many new questions. Here we review emerging uses of urban mobility behaviour data, and propose an analytic framework to represent mobility patterns as a temporal bipartite network between people and places. As this network reconfigures over time, analysts can track experienced inequality along three critical dimensions: social mixing with others from specific demographic backgrounds, access to different types of facilities, and spontaneous adaptation to unexpected events, such as epidemics, conflicts or disasters. This framework traces the dynamic, lived experiences of urban inequality and complements prior work on static inequalities experience at home and work.

Heterogeneous information networks (HIN) have gained increasing popularity in recent years for capturing complex relations between diverse types of nodes. Meta-structures are proposed as a useful tool to identify the important patterns in HINs, but hand-crafted meta-structures pose significant challenges for scaling up, drawing wide research attention towards developing automatic search algorithms. Previous efforts primarily focused on searching for meta-structures with good empirical performance, overlooking the importance of human comprehensibility and generalizability. To address this challenge, we draw inspiration from the emergent reasoning abilities of large language models (LLMs). We propose ReStruct, a meta-structure search framework that integrates LLM reasoning into the evolutionary procedure. ReStruct uses a grammar translator to encode the meta-structures into natural language sentences, and leverages the reasoning power of LLMs to evaluate their semantic feasibility. Besides, ReStruct also employs performance-oriented evolutionary operations. These two competing forces allow ReStruct to jointly optimize the semantic explainability and empirical performance of meta-structures. Furthermore, ReStruct contains a differential LLM explainer to generate and refine natural language explanations for the discovered meta-structures by reasoning through the search history. Experiments on eight representative HIN datasets demonstrate that ReStruct achieves state-of-the-art performance in both recommendation and node classification tasks. Moreover, a survey study involving 73 graduate students shows that the discovered meta-structures and generated explanations by ReStruct are substantially more comprehensible. Our code and questionnaire are available at https://github.com/LinChen-65/ReStruct.

Cities are crucibles of numerous opportunities, but also hotbeds of inequality. The plight of disadvantaged populations who are "left behind" within urban environments has been an increasingly pressing concern, which poses substantial threats to the realization of the UN SDG agenda. However, a comprehensive framework for studying this urban dilemma is currently absent, preventing researchers from developing AI models for social good prediction and intervention. To fill this gap, we construct VulnerabilityMap, a framework to meticulously dissect the challenges faced by urban disadvantaged populations, unraveling their vulnerability to a spectrum of shocks and stresses that are categorized through the prism of Maslow's hierarchy of needs. Specifically, we systematically collect large-scale multi-sourced census and web-based data covering more than 328 million people in the United States regarding demographic features, neighborhood environments, offline mobility behaviors, and online social connections. These features are further related to vulnerability outcomes from short-term shocks such as COVID- 19 and long-term physiological, social, and self-actualization stresses. Leveraging our framework, we construct machine learning models that exhibit strong performance in predicting vulnerability outcomes from various disadvantage features, which shows the promising utility of our framework to support targeted AI models. Moreover, we provide model-based explainability analysis to interpret the reasons underlying model predictions, shedding light on intricate social factors that trap certain populations inside vulnerable situations. Our constructed dataset is publicly available at https://github.com/LinChen-65/VulnerabilityMap/.

Living in cities affords expanded access to various resources, infrastructures, and services at reduced travel costs, which improves social life and promotes systemic gains. However, recent research shows that urban dwellers also experience inequality in accessing urban facilities, which manifests in distinct travel and visitation patterns for residents with different demographic backgrounds. Here, we go beyond simple flawed correlation analysis and reveal prevalent accessibility gaps by quantifying the causal effects of resident demographics on mobility patterns extracted from U.S. residents’ detailed interactions with millions of urban venues. Moreover, to efficiently reveal micro neighborhood-level accessibility gaps, we design a novel Counterfactual RANdom-walks-based Embedding (CRANE) method to learn continuous embedding vectors on urban mobility networks with confounding effects disentangled. Our analysis reveals significant income and racial gaps in mobility frequency and visitation rates to sports and education venues. Besides, bachelor’s degree holders experience greater mobility reduction during the COVID-19 crisis. With extensive experiments on neighborhood-level accessibility prediction and visualizing accessibility gaps with embeddings vectors, we demonstrate that the counterfactual mobility network embeddings can improve the explanatory capacity and robustness of revealed accessibility gaps by extending them from aggregate statistics to individual neighborhoods and allowing for cross-city knowledge transfer. As such, urban mobility networks can reveal consistent accessibility gaps in the U.S., calling for urgent urban design policies to fill in the gaps.

Despite consensus that vaccines play an important role in combatting the global spread of infectious diseases, vaccine inequity is still a prevalent issue due to a deep-seated mentality of self-priority. We aimed to evaluate the existence and possible outcomes of a more equitable global vaccine distribution and explore a concrete incentive mechanism that promotes vaccine equity.

Understanding the impact of COVID-19 on urban life rhythms is crucial for accelerating the return-to-normal progress and envisioning more resilient and inclusive cities. While previous studies either depended on small-scale surveys or focused on the response to initial lockdowns, this paper uses large-scale location service data to systematically analyze the urban mobility behavior changes across three distinct phases of the pandemic, ie, pre-pandemic, lockdown, and reopen. Our analyses reveal two typical patterns that govern the mobility behavior changes in most urban venues: daily life-centered urban venues go through smaller mobility drops during the lockdown and more rapid recovery after reopening, while work-centered urban venues suffer from more significant mobility drops that are likely to persist even after reopening. Such mobility behavior changes exert deeper impacts on the underlying social fabric, where the level of mobility reduction is positively correlated with the experienced segregation at that urban venue. Therefore, urban venues undergoing more mobility reduction are also more filled with people from homogeneous socio-demographic backgrounds. Moreover, mobility behavior changes display significant heterogeneity across geographical regions, which can be largely explained by the partisan inclination at the state level. Our study shows the vast potential of location service data in deriving a timely and comprehensive understanding of the social dynamic in urban space, which is valuable for informing the gradual transition back to the normal lifestyle in a “post-pandemic era”.

Balancing social utility and equity in distributing limited vaccines is a critical policy concern for protecting against the prolonged COVID-19 pandemic and future health emergencies. What is the nature of the trade-off between maximizing collective welfare and minimizing disparities between more and less privileged communities? To evaluate vaccination strategies, we propose an epidemic model that explicitly accounts for both demographic and mobility differences among communities and their associations with heterogeneous COVID-19 risks, then calibrate it with large-scale data. Using this model, we find that social utility and equity can be simultaneously improved when vaccine access is prioritized for the most disadvantaged communities, which holds even when such communities manifest considerable vaccine reluctance. Nevertheless, equity among distinct demographic features may conflict; for example, low-income neighbourhoods might have fewer elder citizens. We design two behaviour-and-demography-aware indices, community risk and societal risk, which capture the risks communities face and those they impose on society from not being vaccinated, to inform the design of comprehensive vaccine distribution strategies. Our study provides a framework for uniting utility and equity-based considerations in vaccine distribution and sheds light on how to balance multiple ethical values in complex settings for epidemic control.

With the advent of the COVID-19 pandemic, the shortage in medical resources became increasingly more evident. Therefore, efficient strategies for medical resource allocation are urgently needed. However, conventional rule-based methods employed by public health experts have limited capability in dealing with the complex and dynamic pandemic-spreading situation. In addition, model-based optimization methods such as dynamic programming (DP) fail to work since we cannot obtain a precise model in real-world situations most of the time. Model-free reinforcement learning (RL) is a powerful tool for decision-making; however, three key challenges exist in solving this problem via RL: (1) complex situations and countless choices for decision-making in the real world; (2) imperfect information due to the latency of pandemic spreading; and (3) limitations on conducting experiments in the real world since we cannot set up pandemic outbreaks arbitrarily. In this article, we propose a hierarchical RL framework with several specially designed components. We design a decomposed action space with a corresponding training algorithm to deal with the countless choices, ensuring efficient and real-time strategies. We design a recurrent neural network–based framework to utilize the imperfect information obtained from the environment. We also design a multi-agent voting method, which modifies the decision-making process considering the randomness during model training and, thus, improves the performance. We build a pandemic-spreading simulator based on real-world data, serving as the experimental platform. We then conduct extensive experiments. The results show that our method outperforms all baselines, which reduces infections and deaths by 14.25% on average without the multi-agent voting method and up to 15.44% with it.

Facing the outbreak of COVID-19, shortage in medical resources becomes increasingly outstanding. Therefore, efficient strategies for medical resource allocation are urgently called for. Reinforcement learning (RL) is powerful for decision making, but three key challenges exist in solving this problem via RL: (1) complex situation and countless choices for decision making in the real world; (2) only imperfect information are available due to the latency of pandemic spreading; (3) limitations on conducting experiments in real world since we cannot set pandemic outbreaks arbitrarily. In this paper, we propose a hierarchical reinforcement learning method with a corresponding training algorithm. We design a decomposed action space to deal with the countless choices to ensure efficient and real time strategies. We also design a recurrent neural network based framework to utilize the imperfect information obtained from the environment. We build a pandemic spreading simulator based on real world data, serving as the experimental platform. We conduct extensive experiments and the results show that our method outperforms all the baselines, which reduces infections and deaths by 14.25% on average.

Facing the worldwide rapid spreading of COVID-19 pandemic, we need to understand its diffusion in the urban environments with heterogeneous population distribution and mobility. However, challenges exist in the choice of proper spatial resolution, integration of mobility data into epidemic modelling, as well as incorporation of unique characteristics of COVID-19. To address these challenges, we build a data-driven epidemic simulator with COVID-19 specific features, which incorporates real-world mobility data capturing the heterogeneity in urban environments. Based on the simulator, we conduct two series of experiments to: (1) estimate the efficacy of different mobility control policies on intervening the epidemic; and (2) study how the heterogeneity of urban mobility affect the spreading process. Extensive results not only highlight the effectiveness of fine-grained targeted mobility control policies, but also uncover different levels of impact of population density and mobility strength on the spreading process. With such capability and demonstrations, our open simulator contributes to a better understanding of the complex spreading process and smarter policies to prevent another pandemic.