arXiv subjects

Jiayi Zhang

Publications and source records attributed to Jiayi Zhang.

At least 73 records · Page 4Linked to original sources

arXiv2026

Understanding Gaming the System by Analyzing Self-Regulated Learning in Think-Aloud Protocols

In digital learning systems, gaming the system refers to occasions when students attempt to succeed in an educational task by systematically taking advantage of system features rather than engaging meaningfully with the content. Often viewed as a form of behavioral disengagement, gaming the system is negatively associated with short- and long-term learning outcomes. However, little research has explored this phenomenon beyond its behavioral representation, leaving questions such as whether students are cognitively disengaged or whether they engage in different self-regulated learning (SRL) strategies when gaming largely unanswered. This study employs a mixed-methods approach to examine students' cognitive engagement and SRL processes during gaming versus non-gaming periods, using utterance length and SRL codes inferred from think-aloud protocols collected while students interacted with an intelligent tutoring system for chemistry. We found that gaming does not simply reflect a lack of cognitive effort; during gaming, students often produced longer utterances, were more likely to engage in processing information and realizing errors, but less likely to engage in planning, and exhibited reactive rather than proactive self-regulatory strategies. These findings provide empirical evidence supporting the interpretation that gaming may represent a maladaptive form of SRL. With this understanding, future work can address gaming and its negative impacts by designing systems that target maladaptive self-regulation to promote better learning.

cs.CY↗

arXiv2026

Using Large Language Models to Detect Socially Shared Regulation of Collaborative Learning

The field of learning analytics has made notable strides in automating the detection of complex learning processes in multimodal data. However, most advancements have focused on individualized problem-solving instead of collaborative, open-ended problem-solving, which may offer both affordances (richer data) and challenges (low cohesion) to behavioral prediction. Here, we extend predictive models to automatically detect socially shared regulation of learning (SSRL) behaviors in collaborative computational modeling environments using embedding-based approaches. We leverage large language models (LLMs) as summarization tools to generate task-aware representations of student dialogue aligned with system logs. These summaries, combined with text-only embeddings, context-enriched embeddings, and log-derived features, were used to train predictive models. Results show that text-only embeddings often achieve stronger performance in detecting SSRL behaviors related to enactment or group dynamics (e.g., off-task behavior or requesting assistance). In contrast, contextual and multimodal features provide complementary benefits for constructs such as planning and reflection. Overall, our findings highlight the promise of embedding-based models for extending learning analytics by enabling scalable detection of SSRL behaviors, ultimately supporting real-time feedback and adaptive scaffolding in collaborative learning environments that teachers value.

cs.LG↗

arXiv2026

ReCode: Unify Plan and Action for Universal Granularity Control

Real-world tasks require decisions at varying granularities, and humans excel at this by leveraging a unified cognitive representation where planning is fundamentally understood as a high-level form of action. However, current Large Language Model (LLM)-based agents lack this crucial capability to operate fluidly across decision granularities. This limitation stems from existing paradigms that enforce a rigid separation between high-level planning and low-level action, which impairs dynamic adaptability and limits generalization. We propose ReCode (Recursive Code Generation), a novel paradigm that addresses this limitation by unifying planning and action within a single code representation. In this representation, ReCode treats high-level plans as abstract placeholder functions, which the agent then recursively decomposes into finer-grained sub-functions until reaching primitive actions. This recursive approach dissolves the rigid boundary between plan and action, enabling the agent to dynamically control its decision granularity. Furthermore, the recursive structure inherently generates rich, multi-granularity training data, enabling models to learn hierarchical decision-making processes. Extensive experiments show ReCode significantly surpasses advanced baselines in inference performance and demonstrates exceptional data efficiency in training, validating our core insight that unifying planning and action through recursive code generation is a powerful and effective approach to achieving universal granularity control. The code is available at https://github.com/FoundationAgents/ReCode.

cs.AI↗

arXiv2025

Atom of Thoughts for Markov LLM Test-Time Scaling

Large Language Models (LLMs) have achieved significant performance gains through test-time scaling methods. However, existing approaches often incur redundant computations due to the accumulation of historical dependency information during inference. To address this challenge, we leverage the memoryless property of Markov processes to minimize reliance on historical context and propose a Markovian reasoning process. This foundational Markov chain structure enables seamless integration with various test-time scaling methods, thereby improving their scaling efficiency. By further scaling up the Markovian reasoning chain through integration with techniques such as tree search and reflective refinement, we uncover an emergent atomic reasoning structure, where reasoning trajectories are decomposed into a series of self-contained, low-complexity atomic units. We name this design Atom of Thoughts (\our). Extensive experiments demonstrate that \our consistently outperforms existing baselines as computational budgets increase. Importantly, \our integrates seamlessly with existing reasoning frameworks and different LLMs (both reasoning and non-reasoning), facilitating scalable, high-performance inference.We submit our code alongside this paper and will make it publicly available to facilitate reproducibility and future research.

cs.CL↗

arXiv2025

Decoding Human and AI Persuasion in National College Debate: Analyzing Prepared Arguments Through Aristotle's Rhetorical Principles

Debate has been widely adopted as a strategy to enhance critical thinking skills in English Language Arts (ELA). One important skill in debate is forming effective argumentation, which requires debaters to select supportive evidence from literature and construct compelling claims. However, the training of this skill largely depends on human coaching, which is labor-intensive and difficult to scale. To better support students in preparing for debates, this study explores the potential of leveraging artificial intelligence to generate effective arguments. Specifically, we prompted GPT-4 to create an evidence card and compared it to those produced by human debaters. The evidence cards outline the arguments students will present and how those arguments will be delivered, including components such as literature-based evidence quotations, summaries of core ideas, verbatim reading scripts, and tags (i.e., titles of the arguments). We compared the quality of the arguments in the evidence cards created by GPT and student debaters using Aristotle's rhetorical principles: ethos (credibility), pathos (emotional appeal), and logos (logical reasoning). Through a systematic qualitative and quantitative analysis, grounded in the rhetorical principles, we identify the strengths and limitations of human and GPT in debate reasoning, outlining areas where AI's focus and justifications align with or diverge from human reasoning. Our findings contribute to the evolving role of AI-assisted learning interventions, offering insights into how student debaters can develop strategies that enhance their argumentation and reasoning skills.

cs.HC↗

arXiv2025

Inhomogeneous Branching Random Walks: Incorporating Genealogy and Density Effects

In this paper, we introduce a novel framework using inhomogeneous Branching Random Walks (BRWs) to model growth processes, specifically introducing genealogy-dependence in branching rates and displacement distributions to model phenomena like bacterial colony growth. Current stochastic models often either assume independent and identical behavior of individual agents or incorporate only spatiotemporal inhomogeneity, ignoring the effect of genealogy-based inhomogeneity on the long-time behavior of these processes. Such long-time asymptotics are of independent mathematical interest and are crucial in understanding the effect of patterns. We propose several inhomogeneous BRW models in 2D space where displacement distributions and branching rates vary with time, space, and genealogy. A combined model then uses a weighted average of positions given by these separate models to study the shape of the growth patterns. Using computer simulations, we tune parameters from these models, which are based on genealogical and spatiotemporal factors, observe the resulting structures, and compare them with images of real bacterial colonies.

q-bio.PE↗

arXiv2025

From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence

Large language models (LLMs) have fundamentally transformed automated software development by enabling direct translation of natural language descriptions into functional code, driving commercial adoption through tools like Github Copilot (Microsoft), Cursor (Anysphere), Trae (ByteDance), and Claude Code (Anthropic). While the field has evolved dramatically from rule-based systems to Transformer-based architectures, achieving performance improvements from single-digit to over 95\% success rates on benchmarks like HumanEval. In this work, we provide a comprehensive synthesis and practical guide (a series of analytic and probing experiments) about code LLMs, systematically examining the complete model life cycle from data curation to post-training through advanced prompting paradigms, code pre-training, supervised fine-tuning, reinforcement learning, and autonomous coding agents. We analyze the code capability of the general LLMs (GPT-4, Claude, LLaMA) and code-specialized LLMs (StarCoder, Code LLaMA, DeepSeek-Coder, and QwenCoder), critically examining the techniques, design decisions, and trade-offs. Further, we articulate the research-practice gap between academic research (e.g., benchmarks and tasks) and real-world deployment (e.g., software-related code tasks), including code correctness, security, contextual awareness of large codebases, and integration with development workflows, and map promising research directions to practical needs. Last, we conduct a series of experiments to provide a comprehensive analysis of code pre-training, supervised fine-tuning, and reinforcement learning, covering scaling law, framework selection, hyperparameter sensitivity, model architectures, and dataset comparisons.

cs.SE↗

arXiv2025

AutoEnv: Automated Environments for Measuring Cross-Environment Agent Learning

Humans naturally adapt to diverse environments by learning underlying rules across worlds with different dynamics, observations, and reward structures. In contrast, existing agents typically demonstrate improvements via self-evolving within a single domain, implicitly assuming a fixed environment distribution. Cross-environment learning has remained largely unmeasured: there is no standard collection of controllable, heterogeneous environments, nor a unified way to represent how agents learn. We address these gaps in two steps. First, we propose AutoEnv, an automated framework that treats environments as factorizable distributions over transitions, observations, and rewards, enabling low-cost (4.12 USD on average) generation of heterogeneous worlds. Using AutoEnv, we construct AutoEnv-36, a dataset of 36 environments with 358 validated levels, on which seven language models achieve 12-49% normalized reward, demonstrating the challenge of AutoEnv-36. Second, we formalize agent learning as a component-centric process driven by three stages of Selection, Optimization, and Evaluation applied to an improvable agent component. Using this formulation, we design eight learning methods and evaluate them on AutoEnv-36. Empirically, the gain of any single learning method quickly decrease as the number of environments increases, revealing that fixed learning methods do not scale across heterogeneous environments. Environment-adaptive selection of learning methods substantially improves performance but exhibits diminishing returns as the method space expands. These results highlight both the necessity and the current limitations of agent learning for scalable cross-environment generalization, and position AutoEnv and AutoEnv-36 as a testbed for studying cross-environment agent learning. The code is avaiable at https://github.com/FoundationAgents/AutoEnv.

cs.AI↗

arXiv2025

Beamforming Design for Beyond Diagonal RIS-Aided Cell-Free Massive MIMO Systems

Reconfigurable intelligent surface (RIS)-aided cell-free (CF) massive multiple-input multiple-output (mMIMO) is a promising technology for further improving spectral efficiency (SE) with low cost and power consumption. However, conventional RIS has inevitable limitations due to its diagonal scattering matrix. In contrast, beyond-diagonal RIS (BD-RIS) has gained great attention. This correspondence focuses on integrating a hybrid transmitting and reflecting BD-RIS into CF mMIMO systems to enhance coverage and spatial multiplexing. This requires completing the beamforming design under the transmit power constraints and unitary constraints of the BD-RIS, by optimizing active and passive beamformer simultaneously. To tackle this issue, we introduce an alternating optimization algorithm that decomposes it using fractional programming and solves the subproblems alternatively. Moreover, to address the challenge introduced by the unitary constraint on the beamforming matrix of the BD-RIS, we propose a Riemannian limited-memory Broyden-Fletcher-Goldfarb-Shanno (R-L-BFGS) algorithm to solve the problem optimally. Simulation results show that our algorithm achieves faster convergence and finds higher-quality solutions compared with baselines, while also demonstrating a favorable performance-complexity trade-off.

cs.IT↗

arXiv2025

Reasoning via Video: The First Evaluation of Video Models' Reasoning Abilities through Maze-Solving Tasks

Video Models have achieved remarkable success in high-fidelity video generation with coherent motion dynamics. Analogous to the development from text generation to text-based reasoning in language modeling, the development of video models motivates us to ask: Can video models reason via video generation? Compared with the discrete text corpus, video grounds reasoning in explicit spatial layouts and temporal continuity, which serves as an ideal substrate for spatial reasoning. In this work, we explore the reasoning via video paradigm and introduce VR-Bench -- a comprehensive benchmark designed to systematically evaluate video models' reasoning capabilities. Grounded in maze-solving tasks that inherently require spatial planning and multi-step reasoning, VR-Bench contains 7,920 procedurally generated videos across five maze types and diverse visual styles. Our empirical analysis demonstrates that SFT can efficiently elicit the reasoning ability of video model. Video models exhibit stronger spatial perception during reasoning, outperforming leading VLMs and generalizing well across diverse scenarios, tasks, and levels of complexity. We further discover a test-time scaling effect, where diverse sampling during inference improves reasoning reliability by 10--20%. These findings highlight the unique potential and scalability of reasoning via video for spatial reasoning tasks.

cs.CV↗

arXiv2025

Identify As A Human Does: A Pathfinder of Next-Generation Anti-Cheat Framework for First-Person Shooter Games

The gaming industry has experienced substantial growth, but cheating in online games poses a significant threat to the integrity of the gaming experience. Cheating, particularly in first-person shooter (FPS) games, can lead to substantial losses for the game industry. Existing anti-cheat solutions have limitations, such as client-side hardware constraints, security risks, server-side unreliable methods, and both-sides suffer from a lack of comprehensive real-world datasets. To address these limitations, the paper proposes HAWK, a server-side FPS anti-cheat framework for the popular game CS:GO. HAWK utilizes machine learning techniques to mimic human experts' identification process, leverages novel multi-view features, and it is equipped with a well-defined workflow. The authors evaluate HAWK with the first large and real-world datasets containing multiple cheat types and cheating sophistication, and it exhibits promising efficiency and acceptable overheads, shorter ban times compared to the in-use anti-cheat, a significant reduction in manual labor, and the ability to capture cheaters who evaded official inspections.

cs.CR↗

arXiv2025

Understanding and Mitigating Political Stance Cross-topic Generalization in Large Language Models

Fine-tuning Large Language Models on a political topic will significantly manipulate their political stance on various issues and unintentionally affect their stance on unrelated topics. While previous studies have proposed this issue, there is still a lack of understanding regarding the internal representations of these stances and the mechanisms that lead to unintended cross-topic generalization. In this paper, we systematically explore the internal mechanisms underlying this phenomenon from a neuron-level perspective and how to mitigate the cross-topic generalization of political fine-tuning. Firstly, we propose Political Neuron Localization through Activation Contrasting (PNLAC) to identify two distinct types of political neurons: general political neurons, which govern stance across multiple political topics, and topic-specific neurons} that affect the model's political stance on individual topics. We find the existence of these political neuron types across four models and datasets through activation patching experiments. Leveraging these insights, we introduce InhibitFT, an inhibition-based fine-tuning method, effectively mitigating the cross-topic stance generalization. Experimental results demonstrate the robustness of identified neuron types across various models and datasets, and show that InhibitFT significantly reduces the cross-topic stance generalization by 20% on average, while preserving topic-specific performance. Moreover, we demonstrate that selectively inhibiting only 5% of neurons is sufficient to effectively mitigate the cross-topic stance generalization.

cs.CL↗

arXiv2025

Opinion: Towards Unified Expressive Policy Optimization for Robust Robot Learning

Offline-to-online reinforcement learning (O2O-RL) has emerged as a promising paradigm for safe and efficient robotic policy deployment but suffers from two fundamental challenges: limited coverage of multimodal behaviors and distributional shifts during online adaptation. We propose UEPO, a unified generative framework inspired by large language model pretraining and fine-tuning strategies. Our contributions are threefold: (1) a multi-seed dynamics-aware diffusion policy that efficiently captures diverse modalities without training multiple models; (2) a dynamic divergence regularization mechanism that enforces physically meaningful policy diversity; and (3) a diffusion-based data augmentation module that enhances dynamics model generalization. On the D4RL benchmark, UEPO achieves +5.9\% absolute improvement over Uni-O4 on locomotion tasks and +12.4\% on dexterous manipulation, demonstrating strong generalization and scalability.

cs.RO↗

arXiv2025

Multi-modal Dynamic Proxy Learning for Personalized Multiple Clustering

Multiple clustering aims to discover diverse latent structures from different perspectives, yet existing methods generate exhaustive clusterings without discerning user interest, necessitating laborious manual screening. Current multi-modal solutions suffer from static semantic rigidity: predefined candidate words fail to adapt to dataset-specific concepts, and fixed fusion strategies ignore evolving feature interactions. To overcome these limitations, we propose Multi-DProxy, a novel multi-modal dynamic proxy learning framework that leverages cross-modal alignment through learnable textual proxies. Multi-DProxy introduces 1) gated cross-modal fusion that synthesizes discriminative joint representations by adaptively modeling feature interactions. 2) dual-constraint proxy optimization where user interest constraints enforce semantic consistency with domain concepts while concept constraints employ hard example mining to enhance cluster discrimination. 3) dynamic candidate management that refines textual proxies through iterative clustering feedback. Therefore, Multi-DProxy not only effectively captures a user's interest through proxies but also enables the identification of relevant clusterings with greater precision. Extensive experiments demonstrate state-of-the-art performance with significant improvements over existing methods across a broad set of multi-clustering benchmarks.

cs.LG↗

arXiv2025

Large Language Model Empowered Next-Generation MIMO Networks: Fundamentals, Challenges, and Visions

Next-generation Multiple-Input Multiple-Output (MIMO) is expected to be intelligent and scalable. In this paper, we study Large Language Model (LLM)-enabled next-generation MIMO networks. Firstly, we provide an overview of the development, fundamentals, and challenges of the next-generation MIMO. Then, we propose the concept of the generative AI agent, which is capable of generating tailored and specialized contents with the aid of LLM and Retrieval Augmented Generation (RAG). Next, we comprehensively discuss the features and advantages of the generative AI agent framework. More importantly, to tackle existing challenges of next-generation MIMO, we discuss generative AI agent-enabled next-generation MIMO networks from the perspective of performance analysis, signal processing, and resource allocation. Furthermore, we present two compelling case studies that demonstrate the effectiveness of leveraging the generative AI agent for performance analysis in complex configuration scenarios. These examples highlight how the integration of generative AI agents can significantly enhance the analysis and design of next-generation MIMO systems. Finally, we discuss important potential research future directions.

cs.NI↗

arXiv2025

Flexible MIMO for Future Wireless Communications: Which Flexibilities are Possible?

In conventional multiple-input multiple-output (MIMO), static array configurations struggle in dynamic environments, and further antenna scaling is bounded by cost, energy, and footprint. Emerging approaches, which can enable next-generation wireless communication networks with modest spectrum availability by leveraging flexibility and adaptability rather than sheer array growth, are therefore needed. In this paper, we present a taxonomy framework, referred to as flexible MIMO technology, that systematically categorizes a wide range of evolving MIMO technologies. The focus is on MIMO technologies with flexible physical configurations and integrated applications. We categorize twelve representative flexible MIMO technologies into three major classifications: flexible deployment characteristics-based, flexible geometry characteristics-based, and flexible real-time modifications-based. We then comprehensively overview their fundamental characteristics, potential, and challenges. In addition, we highlight three vital enablers for flexible MIMO technology, including efficient channel state information acquisition schemes, low-complexity beamforming design, and explainable artificial intelligence (AI)-enabled optimization, and discuss eight representative sub-techniques. Finally, two brief case studies -- pre-optimized irregular array for high-speed railway network and cell-free movable antenna -- are presented, showing how flexible MIMO can open new design possibilities and inspire future research directions for next-generation wireless networks.

cs.IT↗

arXiv2025

Time-harmonic scattering of plane waves from an infinite periodically inhomogeneous medium

We propose a new radiation condition for an infinite inhomogeneous two-dimensional medium which is periodic in the vertical direction and remains invariant in the horizontal direction. The classical Rayleigh-expansion radiation condition does not apply to our case, because this would require the medium to be inhomogeneous in a half plane. We utilize the Floquet theory to derive upward/downward wave modes and define radiation conditions by expansions w.r.t. these modes. The downward radiation conditions leads to a downward Dirichlet-to-Neumann map which can be used to truncate the infinite inhomogeneous domain in the vertical direction. So we prove mapping properties of the upward/downward Dirichlet-to-Neumann maps based on the asymptotic behavior of high-order wave modes. Finally, we verify the strong ellipticity of the sesquilinear form corresponding to the new scattering problem and show the unique solvability for all wavenumbers with the exception of a countable set of numbers bounded below by a small positive constant.

math.AP↗

arXiv2025

Stacked Intelligent Metasurfaces for 6G Wireless Networks: Principles, Applications, and Research Directions

The sixth-generation (6G) wireless networks are expected to deliver ubiquitous connectivity, resilient coverage, and intelligence-driven services in highly dynamic environments. To achieve these goals, distributed wireless architectures such as cell-free massive multiple-input multiple-output (MIMO) have attracted significant attention due to their scalability and fairness. Recently, stacked intelligent metasurfaces (SIMs) have emerged as a promising evolution of reconfigurable intelligent surfaces, offering multi-layer electromagnetic domain processing with enhanced controllability and spatial degrees of freedom. By integrating SIMs into distributed wireless networks, advanced wave-domain operations can be realized, enabling efficient interference management, improved energy and spectral efficiency, and robust physical-layer security. This article provides a comprehensive overview of SIM-aided distributed wireless networks, including their application scenarios, classification, and system architectures. Key signal processing challenges, such as hierarchical frameworks, user association, and joint precoding, are discussed, followed by case studies demonstrating significant performance gains. Finally, future research directions in hardware design, energy consumption modeling, algorithm development, and artificial intelligence integration are highlighted, aiming to pave the way for scalable and intelligent 6G distributed wireless networks.

cs.IT↗