Adaptive Learning Systems (ALS) play a key role in promoting the equity of education, which can provide personalized teaching on a large scale. However, the existing question recommendation methods face the problem of data sparsity at the scenario of cold-start, and lack the ability of long-term teaching reasoning. To address these challenges, we propose QuesRecAgent, a multi-agent framework which involves Large Language Models (LLMs) and the Relexion mechanism for adaptive question recommendation. Different from the traditional black-box methods, the QuesRecAgent applies a framework Dual-Loop State Decoupling architecture, which achieves a rapid updating of beliefs through simulated interaction in the inner loop and do the authoritative diagnosis and meta-strategy reflection to optimize the teaching strategy in the outer loop. Furthermore, with the support of a Topological Knowledge Graph (TKG) and the theory of Zone of Proximal Development (ZPD), the QuesRecAgent ensures a high-quality learning guidance even facing students with limited interaction records. Our experiments on three real-world datasets show that the QuesRecAgent outperforms state-of-the-art baselines in total knowledge gain and other metrics, providing a robust and interpretable solution for promoting high-quality personalized education.
论文检索
输入标题、作者或关键词，从 4,693 篇学术成果中精准定位
Reward learning via human feedback is a crucial capability for beneficial AI. Current methods are built on decision-making theories that assume a matched dynamics model between the learning agent and the feedback provider. However, humans often form imperfect internal dynamics models, and their feedback reflects these misconceptions. While this relationship has long been hypothesised, its manifestation in sequential decision-making remains largely an assumption. Our work provides the first comprehensive empirical investigation of this relationship through a randomized controlled trial (N=211). We followed a two-stage design where we first initialized the participants' understanding of the dynamics in a grid-world navigation domain and then manipulated it using text-based instructions. Causal mediation analysis revealed that humans' internal models play a mediating role in feedback behaviour. We show that this relationship is invariant across visual contexts and is robust to three common feedback types: pairwise preferences, trajectory corrections, and off-switch interventions. These findings confirm a critical limitation of current reward learning methods and establish the missing psychological foundation for approaches that incorporate dynamics understanding.
For minimally rigid graphs, the same edge-length data can admit multiple realizations (up to translations and rotations). Finding graphs with exceptionally many realizations is an extremal problem in rigidity theory, but exhaustive search quickly becomes infeasible due to the super-exponential growth of the number of candidate graphs and the high cost of realization-count evaluation. We propose a reinforcement-learning approach that constructs minimally rigid graphs via 0- and 1-extensions, also known as Henneberg moves. We optimize realization-count invariants using the Deep Cross-Entropy Method with a policy parameterized by a Graph Isomorphism Network encoder and a permutation-equivariant extension-level action head. Empirically, our method matches the known optima for planar realization counts and improves the best known bounds for spherical realization counts, yielding new record graphs.
Coverage-based prime implicant explanations are formal explanations offering a number of valuable assets, especially in terms of faithfulness and generality. Unfortunately, deriving a coverage-based prime implicant explanation for an instance is computationally hard in the general case (the problem of identifying such an explanation being at the second level of the polynomial hierarchy). In this paper, we focus on the computation of a coverage-based prime implicant explanation for an instance given a tree-based model. We show that the specific nature of the domain theory linking the Boolean conditions in such models makes the problem computationally easier. We present a greedy algorithm to derive coverage-based prime implicant explanations when dealing with a tree-based model. We also present an empirical evaluation showing that this algorithm is efficient enough to be used in many practical cases.
Artificial intelligence models typically perform well on large-scale datasets, yet their effectiveness tends to degrade in real-world scenarios with scarce data, such as medical diagnostics. In contrast, humans can learn and reason effectively from few examples. Even when novel objects differ significantly from prior observations, humans can quickly infer category distributions accurately. Inspired by this, we explore how to leverage human-inspired cognitive mechanisms to improve the distribution calibration in few-shot learning models. Based on the ``fast-slow thinking'' dual-process theory, we propose a novel cognition-inspired few-shot learning framework. It mimics the human cognition when handling novel information: it first rapidly screens relevant knowledge through ``fast thinking'' and then infers inter-class relationships and calibrates distributions via ``slow thinking''. Specifically, the fast-thinking stage employs a gating mechanism to quickly match input samples with known base-class prototypes, activating relevant candidate knowledge. In the slow-thinking stage, the model aggregates inter-class edge embeddings into a summary relation graph and then applies divergent Gaussian sampling to generate multiple relation graphs representing different association strengths, thereby achieving distribution calibration for few-shot classes. Experiments on public few-shot benchmarks and medical image datasets show competitive performance. Visualization analyses further reveal that our framework exhibits meaningful interpretability.
Knowledge Tracing (KT) is fundamental to intelligent education systems, yet relies on educational logs that are selectively observed. The non-random nature of exercise recommendations and student choices inevitably induces severe selection bias. Most existing KT methods neglect this issue, training on observed logs using standard empirical risk, which yields biased mastery estimates and accumulates errors in subsequent recommendations. To address this, we introduce a doubly robust (DR) formulation for KT that integrates a propensity model with an error imputation model, theoretically guaranteeing unbiasedness if either model is accurate. Beyond unbiasedness, in the sequential setting of KT, we identify that the estimator's performance is compromised by variance-dependent stochastic deviations that accumulate over time, thereby causing training instability and limiting performance. To mitigate this, we derive a generalization bound that explicitly characterizes the impact of estimator variance and identifies temporal smoothness as a key factor in controlling it. Building on these theoretical insights, we propose the Temporal Smoothness Doubly Robust (TSDR) framework. TSDR jointly optimizes the KT predictor and the imputation model with a smoothness regularizer, effectively reducing variance while preserving the unbiasedness guarantee of DR. Experiments on multiple real-world benchmarks demonstrate that TSDR consistently enhances various state-of-the-art KT backbones, underscoring the vital role of principled bias correction in KT.
We investigate the complexity of stable (or perturbation-resilient) instances of k-Means and k-Median clustering problems in metrics with small doubling dimension. While these problems have been extensively studied under multiplicative perturbation resilience in low-dimensional Euclidean spaces, we adopt a more general notion of stability, termed "almost stable", known from the literature as (alpha,epsilon)-perturbation resilience. Additionally, we extend our results to k-Means/k-Median with penalties, where each data point is either assigned to a cluster centre or incurs a penalty. We show that certain special cases of almost stable k-Means/k-Median (with penalties) are solvable in polynomial time. To complement this, we also examine the hardness of almost stable instances and (1 + 1/poly(n))-stable instances of k-Means/k-Median (with penalties), proving super-polynomial lower bounds on the runtime of any exact algorithm under the widely believed Exponential Time Hypothesis (ETH).
Multi-label data often contain high-dimensional features, outlier instances, and noisy labels, all of which can lead to the curse of dimensionality and decreased performance in downstream tasks. Although numerous data reduction methods have been developed, existing approaches face two major limitations: 1) existing methods typically select features, instances, or labels independently, without considering how noise or redundancy in one dimension may negatively influence the selection of others; 2) there are very few feature and instance co-selection methods that commonly assume label annotations are free of noise, which is seldom true in practice. To address these issues, we propose Evidential Multi-Label Multi-Dimensional Selection (EMMS), which jointly performs feature, instance, and label selection on multi-label data. EMMS introduces a dual projection mechanism with sparsity constraints that transforms high-dimensional data first into a latent space and then into the label space. Simultaneously, projection residuals are explicitly modeled to facilitate the identification of representative instances, enabling unified selection across features, instances, and labels. Moreover, EMMS employs evidence theory to fuse instance-level and label-level evidence, thereby enhancing the reliability of the learned labels and reducing the influence of noisy labels, which in turn promotes multi-dimensional selection. Extensive experiments demonstrate that EMMS consistently outperforms state-of-the-art methods.
The Spherical Sliced Wasserstein (SSW) distance has emerged as a fundamental tool for comparing probability measures on the hypersphere, with broad applications spanning geology, medical imaging, computer vision, and representation learning. However, its reliance on uniformly sampling a large number of projection directions from the unit hypersphere can lead to suboptimal performance, as many directions are weakly informative and fail to capture salient differences between distributions. We address this limitation through Fusion Stereographic Spherical Sliced Wasserstein (FS3W), a data-adaptive divergence that incorporates distribution-dependent information into projection selection. FS3W uses a neural slicing fusion mechanism to refine prior directions, steering them toward projections aligned with discriminative geometric structures in the data. This adaptive approach produces more expressive and accurate characterizations of distributional discrepancies on the hypersphere. We evaluate FS3W across five diverse tasks, including gradient flows, Earth density estimation, and self-supervised representation learning. Empirical results consistently demonstrate that FS3W outperforms existing spherical optimal transport–based methods.
Many practical decision-making problems involve tasks whose success depends on the entire system history, rather than on achieving a state with desired properties. Markovian Reinforcement Learning (RL) can be inadequate for such tasks, while modeling them as non-Markovian reward decision processes (NMRDPs) enables agents to handle temporal dependencies. Existing approaches offer limited formal guarantees on both (near-)optimality and sample efficiency. We address both issues with QR-max, a novel model-based algorithm for NMRDPs with discrete actions that factorizes Markovian transition learning from non-Markovian reward handling via reward machines. To our knowledge, this is the first model-based RL algorithm for discrete-action NMRDPs that leverages this factorization to obtain PAC convergence to ε-optimal policies with polynomial sample complexity. We then extend QR-max to continuous state spaces with Bucket-QR-max, a SimHash-based discretizer that preserves the same factorized structure and achieves fast and stable learning without manual gridding or function approximation. We experimentally compare our method with state-of-the-art model-based RL approaches on environments of increasing complexity, showing substantially improved sample efficiency and greater robustness in finding optimal policies.
Stochastic gradient methods are central to large-scale learning, yet their generalization theory typically relies on independent sampling assumptions. In many practical applications, data are generated by Markov chains and learning is performed in a decentralized manner, which introduces significant analytical challenges. In this work, we investigate the stability and generalization of decentralized stochastic gradient descent (SGD) and stochastic gradient descent ascent (SGDA) under Markov chain sampling. Leveraging a stability-based framework, we characterize how Markovian dependence and decentralized communication jointly influence generalization behavior. Our analysis captures the effects of network topology, Markov chain mixing properties, and primal–dual dynamics. We establish non-asymptotic generalization bounds for both algorithms, extending existing results on Markov stochastic gradient methods to decentralized and minimax settings.
Open-vocabulary 3D understanding aims to align 3D representations with a unified vision-language semantic space. However, existing methods suffer from the challenge of structural asymmetry caused by sparse observations and holistic geometries. Additionally, the inherent semantic chasm between discrete coordinates and abstract natural language hinders cross-modal mapping. This work introduces SpecBridge, a 3D-2D-Text pre-training framework that leverages CLIP priors as a foundational bridge to connect three modalities by synergizing spectral graph theory with transitive semantic learning. The method consists of two main sub-modules. First, Spectral Eigen-Modal Alignment is presented to construct cross-modal correlations within the intrinsic eigen-spectral space via Laplacian eigendecomposition. By aligning low-frequency geometric harmonics with CLIP-guided observation inference, it maintains structural consistency between 3D geometries and 2D projections. Second, a Transitive Spectral-Semantic Alignment method is developed to establish a 3D→2D→Text propagation chain across the CLIP priors bridge. It distills dense CLIP priors into 3D representations through transitive distillation, effectively mitigating the semantic chasm between geometry and language. Extensive experiments confirm that the proposed SpecBridge demonstrates state-of-the-art performance by overcoming challenges triggered by modality discrepancies.
Test-time scaling (TTS) has demonstrated remarkable potential in enhancing the reasoning capabilities of Large Language Models (LLMs) and Large Vision-Language Models (LVLMs). However, its application has primarily been limited to domains such as mathematics and programming, owing to their reasoning-intensive nature and the ease of result verification. Its utility in other knowledge-intensive fields, such as medicine and general scientific research, remains underexplored. To bridge this gap and unlock the potential of TTS in broader domains, we propose Cross-Domain TTS, a novel framework that enables task-tailored scaling. This framework consists of two key components: a conformal prediction-based cold-start strategy and an information-gain-based dynamic reasoning adjustment. The CP-based cold-start strategy guides the model's initialization during test-time scaling based on conformal prediction theory, while the information-gain-based dynamic reasoning adjustment guides the model's reasoning progress through a progress vector according to the information gain of reasoning steps. We conducted experiments using LLMs and LVLMs on cross-domain benchmarks. Our results demonstrate that the proposed framework consistently improves performance across various domain-specific datasets. For instance, in the medical domain, it achieves an improvement of up to 17% in pass@1 accuracy while reducing inference latency and saving up to 30% in token consumption. Code is available at https://github.com/Yan0613/Cross-Domain-TTS.
Stochastic games have become a prevalent framework for studying long-term multi-agent interactions, especially in the context of multi-agent reinforcement learning. In this work, we comprehensively investigate the concept of constant-memory strategies in stochastic games. We first establish some results on best responses and Nash equilibria for behavioral constant-memory strategies, followed by a discussion on the computational hardness of best responding to mixed constant-memory strategies. Those theoretic insights are later verified on several sequential decision-making testbeds, including the Iterated Prisoner's Dilemma, the Iterated Traveler's Dilemma, and the Pursuit domain. This work aims to enhance the understanding of theoretical issues in single-agent planning under multi-agent systems, and uncover the connection between decision models in single-agent and multi-agent contexts. The codebase and the full version of this paper is available at github.com/Fernadoo/Const-Mem.
Learning to Defer operates by deferring AI-uncertain samples to humans, enabling the system to outperform either alone. Some works extend it by introducing human-AI combination to deferral. However, they remain limited to binary choices. Given that AI, humans, and human-AI combination are each indispensable, we extend the binary deferral paradigm to a ternary one. There are two challenges: i) how to effectively select among the three modes, especially distinguishing humans from combination? ii) how to design an enhanced combination without being degraded by unreliable model predictions? To address the challenges, we propose TriHAI, a tri-mode deferral method that routes samples to suitable modes based on normalized confidence scores obtained through a discriminative gating network, and enhances combination mode by fusing model predictions refined by human-guided Conformal Prediction and human predictions via Bayesian theory. Experiments on three datasets show that TriHAI surpasses other human-AI baselines by up to 9.57% in accuracy.
Transformers have reshaped modern artificial intelligence, yet their theoretical foundations remain incomplete. This thesis investigates the approximation power and memory limitations of transformers. I combine tools from approximation theory and statistical learning theory to provide provable guarantees on expressivity, memorization capacity, and inherent architectural constraints. My contributions include the first rigorous proof of memory bottlenecks in prompt tuning and new results on the expressivity of transformers. The long-term goal of my doctoral research is to develop a principled theoretical framework that grounds the empirical behavior of large-scale transformer models in formal approximation-theoretic results.
SlideBot: A Multi-Agent Framework for Generating Informative, Reliable, Multi-Modal Presentations
PDF ↗Large Language Models (LLMs) have shown immense potential in education, automating tasks like quiz generation and content summarization. However, generating effective presentation slides introduces unique challenges due to the complexity of multimodal content creation and the need for precise, domain-specific information. Existing LLM-based solutions often fail to produce reliable and informative outputs, limiting their educational value. To address these limitations, we introduce SlideBot - a modular, multi-agent slide generation framework that integrates LLMs with retrieval, structured planning, and code generation. SlideBot is organized around three pillars: informativeness, ensuring deep and contextually grounded content; reliability, achieved by incorporating external sources through retrieval; and practicality, which enables customization and iterative feedback through instructor collaboration. It incorporates evidence-based instructional design principles from Cognitive Load Theory (CLT) and the Cognitive Theory of Multimedia Learning (CTML), using structured planning to manage intrinsic load and consistent visual macros to reduce extraneous load and enhance dual-channel learning. Within the system, specialized agents collaboratively retrieve information, summarize content, generate figures, and format slides using LaTeX, aligning outputs with instructor preferences through interactive refinement. Evaluations from domain experts and students in AI and biomedical education show that SlideBot consistently enhances conceptual accuracy, clarity, and instructional value. These findings demonstrate SlideBot’s potential to streamline slide preparation while ensuring accuracy, relevance, and adaptability in higher education.
Thinking Through the Hands: An Exploratory Study of Hand Movements to Assess Students Problem-Solving in Mechanistic Reasoning Tasks
PDF ↗Theories of embodied learning emphasize that learning processes are grounded in bodily actions and interactions with the environment, suggesting that movements play a fundamental role in problem solving, decision making, and learning. This perspective holds particular relevance for making-based learning settings, where patterns of movement and spatial engagement can reveal strategic expertise. Prior research has examined distinctions between students who learned and did not learn, but manual coding of actions presents scalability and real-time application challenges. To address this gap, we develop a computer vision–based analysis pipeline for automated detection and characterization of hand movements during complex assembly tasks. In an exploratory study, we apply this approach to video data of students engaged in the assembly of a differential gearbox, quantifying metrics such as amount and speed of movement. Results indicate that learners show fewer right-hand movements than novices and exhibit reduced movement speed, with a progressive decline in speed as the task unfolds. Non-learners, by contrast, display more uneven hand movement speed. These findings, while preliminary, highlight measurable differences in actions of learners and non-learners, and therefore have potential implications for learning support. Specifically, the ability to computationally distinguish movement profiles can inform the design of adaptive learning interventions, providing real-time performance assessment and targeted feedback for making-based learning.
Multiagent systems is a key area within artificial intelligence (AI) that explores the behavior of interacting rational agents where the decisions of one agent impact others. Rooted in economic game theory, multiagent systems takes the idea of individual incentives from economic game theory and applies it to distributed computation and decentralized mechanisms. It examines not only how certain overall economic or computational goals can be accomplished, but also why individual participants will choose to cooperate with reaching that goal. While multiagent systems is grounded in rigorous mathematical theory, current pedagogical approaches often lack opportunities for students to connect abstract theory with real-world human dynamics. This disconnect is particularly pressing as AI increasingly operates in sociotechnical environments, where understanding human behavior and interaction is critical. This paper presents the first exploration of using large participation activities to facilitate experiential learning to bridge this gap. We report on a day-long resource allocation scenario involving up to 43 participants, designed to simulate multiagent interactions under pressure and with meaningful stakes, where learners can apply their theoretical knowledge to analyze and solve emerging problems. We propose ``megagames'' as a powerful pedagogical tool not only for multiagent systems, but also for other domains as well.
Recent work has explored the interests that draw learners to Machine Learning (ML), aiming to support their success and broaden participation in the field. However, whether strategies used in textbooks align with these interests is unexplored. We perform a thematic analysis of the introductions from ten openly available ML textbooks to identify their motivational strategies and compare them with student interests documented in prior research. We find that textbooks frequently motivate learners in their introductions by setting learning goals, previewing core ML topics to be covered, showcasing applications and current successes, and, less often, by using learner-centered strategies such as reassurance or curiosity prompts. We group these motivations into three overarching themes: theoretical, practical, and learner-centered. These motivations largely align with student interests, particularly in theory and applications, even in textbooks published before the recent surge of ML and Artificial Intelligence. These findings reveal how textbooks frame ML’s value and offer evidence-based guidance for developing future materials that better engage and support diverse learners.