CASTLE: A Comprehensive Benchmark for Evaluating Student-Tailored Personalized Safety in Large Language Models

Large language models (LLMs) have advanced the development of personalized learning in education. However, their inherent generation mechanisms often produce homogeneous responses to identical prompts. This one-size-fits-all mechanism overlooks the substantial heterogeneity in students cognitive and psychological, thereby posing potential safety risks to vulnerable groups. Existing safety evaluations primarily rely on context-independent metrics such as factual accuracy, bias, or toxicity, which fail to capture the divergent harms that the same response might cause across different student attributes. To address this gap, we propose the concept of Student-Tailored Personalized Safety and construct CASTLE based on educational theories. This benchmark covers 15 educational safety risks and 14 student attributes, comprising 92,908 bilingual scenarios. We further design three evaluation metrics: Risk Sensitivity, measuring the model ability to detect risks; Emotional Empathy, evaluating the model capacity to recognize student states; and Student Alignment, assessing the match between model responses and student attributes. Experiments on 18 SOTA LLMs demonstrate that CASTLE poses a significant challenge: all models scored below an average safety rating of 2.3 out of 5, indicating substantial deficiencies in personalized safety assurance.

Workflow-R1: Group Sub-sequence Policy Optimization for Multi-turn Workflow Construction

The rapid evolution of agentic workflows has demonstrated strong performance of LLM-based agents in addressing complex reasoning tasks. However, existing workflow optimization methods typically formulate workflow synthesis as a static, one-shot code-centric generation problem. This paradigm imposes excessive constraints on the model's coding capabilities and restricts the flexibility required for dynamic problem-solving. In this paper, we present Workflow-R1, a framework that reformulates workflow construction as a multi-turn, natural language-based sequential decision-making process. To resolve the optimization granularity mismatch inherent in such multi-turn interactions, we introduce Group Sub-sequence Policy Optimization (GSsPO). While explicitly tailored to align with the interleaved Think-Action dynamics of agentic reasoning, GSsPO fundamentally functions as a structure-aware RL algorithm generalizable to a broad class of multi-turn agentic sequential decision-making tasks. By recalibrating the optimization unit to the composite sub-sequence, specifically the atomic Think-Action cycle, it aligns gradient updates with the semantic boundaries of these interactions, ensuring robust learning in complex multi-turn reasoning tasks. Through extensive experiments on multiple QA benchmarks, Workflow-R1 outperforms competitive baselines, validating GSsPO as a generalized solution for sequential reasoning and establishing Workflow-R1 as a promising new paradigm for automated workflow optimization.

Real-Time Aligned Reward Model beyond Semantics

Reinforcement Learning from Human Feedback (RLHF) is a pivotal technique for aligning large language models (LLMs) with human preferences, yet it is susceptible to reward overoptimization, in which policy models overfit to the reward model, exploit spurious reward patterns instead of faithfully capturing human intent. Prior mitigations primarily relies on surface semantic information and fails to efficiently address the misalignment between the reward model (RM) and the policy model caused by continuous policy distribution shifts. This inevitably leads to an increasing reward discrepancy, exacerbating reward overoptimization. To address these limitations, we introduce R2M (Real-Time Aligned Reward Model), a novel lightweight RLHF framework. R2M goes beyond vanilla reward models that solely depend on the semantic representations of a pretrained LLM. Instead, it leverages the evolving hidden states of the policy (namely policy feedback) to align with the real-time distribution shift of the policy during the RL process. This work points to a promising new direction for improving the performance of reward models through real-time utilization of feedback from policy models.

UCO: A Multi-Turn Interactive Reinforcement Learning Method for Adaptive Teaching with Large Language Models

Large language models (LLMs) are shifting from answer providers to intelligent tutors in educational settings, yet current supervised fine-tuning methods only learn surface teaching patterns without dynamic adaptation capabilities. Recent reinforcement learning approaches address this limitation but face two critical challenges. First, they evaluate teaching effectiveness solely based on whether students produce correct outputs, unable to distinguish whether students genuinely understand or echo teacher-provided answers during interaction. Second, they cannot perceive students' evolving cognitive states in real time through interactive dialogue, thus failing to adapt teaching strategies to match students' cognitive levels dynamically. We propose the Unidirectional Cognitive Optimization (UCO) method to address these challenges. UCO uses a multi-turn interactive reinforcement learning paradigm where the innovation lies in two synergistic reward functions: the Progress Reward captures students' cognitive advancement, evaluating whether students truly transition from confusion to comprehension, while the Scaffold Reward dynamically identifies each student's Zone of Proximal Development (ZPD), encouraging teachers to maintain productive teaching within this zone. We evaluate UCO by comparing it against 11 baseline models on BigMath and MathTutorBench benchmarks. Experimental results demonstrate that our UCO model outperforms all models of equivalent scale and achieves performance comparable to advanced closed-source models. The code and data are available at https://github.com/Mind-Lab-ECNU/UCO.

EduAgentQG: A Multi-Agent Workflow Framework for Personalized Question Generation

High-quality personalized question banks are crucial for supporting adaptive learning and individualized assessment. Manually designing questions is time-consuming and often fails to meet diverse learning needs, making automated question generation a crucial approach to reduce teachers' workload and improve the scalability of educational resources. However, most existing question generation methods rely on single-agent or rule-based pipelines, which still produce questions with unstable quality, limited diversity, and insufficient alignment with educational goals. To address these challenges, we propose EduAgentQG, a multi-agent collaborative framework for generating high-quality and diverse personalized questions. The framework consists of five specialized agents and operates through an iterative feedback loop: the Planner generates structured design plans and multiple question directions to enhance diversity; the Writer produces candidate questions based on the plan and optimizes their quality and diversity using feedback from the Solver and Educator; the Solver and Educator perform binary scoring across multiple evaluation dimensions and feed the evaluation results back to the Writer; the Checker conducts final verification, including answer correctness and clarity, ensuring alignment with educational goals. Through this multi-agent collaboration and iterative feedback loop, EduAgentQG generates questions that are both high-quality and diverse, while maintaining consistency with educational objectives. Experiments on two mathematics question datasets demonstrate that EduAgentQG outperforms existing single-agent and multi-agent methods in terms of question diversity, goal consistency, and overall quality.

ActiveDPO: Active Direct Preference Optimization for Sample-Efficient Alignment

The recent success of using human preferences to align large language models (LLMs) has significantly improved their performance in various downstream tasks like question answering, mathematical reasoning, and code generation. However,3 achieving effective LLM alignment depends on high-quality human preference datasets. Collecting these datasets requires human preference annotation, which is costly and resource-intensive, necessitating efficient active data selection methods. Existing methods either lack a strong theoretical foundation or depend on restrictive reward function assumptions (e.g., linearity). To this end, we propose an algorithm, ActiveDPO, that uses a theoretically grounded data selection criterion for non-linear reward functions while directly leveraging the LLM itself to parameterize the reward model that is used for active data selection. As a result, ActiveDPO explicitly accounts for the influence of LLM on data selection, unlike methods that select the data without considering the LLM that is being aligned, thereby leading to more effective and efficient data collection. Extensive experiments show that ActiveDPO outperforms existing methods across various models and datasets.

Convergence Rates of Constrained Expected Improvement

Constrained Bayesian optimization (CBO) methods have seen significant success in black-box optimization with constraints, and one of the most commonly used CBO methods is the constrained expected improvement (CEI) algorithm. CEI is a natural extension of the expected improvement (EI) when constraints are incorporated. However, the theoretical convergence rate of CEI has not been established. In this work, we study the convergence rate of CEI by analyzing its simple regret upper bound. First, we show that when the objective function $f$ and constraint function $c$ are assumed to each lie in a reproducing kernel Hilbert space (RKHS), CEI achieves the convergence rates of $\mathcal{O} \left(t^{-\frac{1}{2}}\log^{\frac{d+1}{2}}(t) \right) \ \text{and }\ \mathcal{O}\left(t^{\frac{-\nu}{2\nu+d}} \log^{\frac{\nu}{2\nu+d}}(t)\right)$ for the commonly used squared exponential and Mat\'{e}rn kernels, respectively. Second, we show that when $f$ and $c$ are assumed to be sampled from Gaussian processes (GPs), CEI achieves the same convergence rates with a high probability. Numerical experiments are performed to validate the theoretical analysis.

Active Human Feedback Collection via Neural Contextual Dueling Bandits

Collecting human preference feedback is often expensive, leading recent works to develop principled algorithms to select them more efficiently. However, these works assume that the underlying reward function is linear, an assumption that does not hold in many real-life applications, such as online recommendation and LLM alignment. To address this limitation, we propose Neural-ADB, an algorithm based on the neural contextual dueling bandit framework that provides a principled and practical method for collecting human preference feedback when the underlying latent reward function is non-linear. We theoretically show that when preference feedback follows the Bradley-Terry-Luce model, the worst sub-optimality gap of the policy learned by Neural-ADB decreases at a sub-linear rate as the preference dataset increases. Our experimental results on problem instances derived from synthetic preference datasets further validate the effectiveness of Neural-ADB.

Online Clustering of Dueling Bandits

The contextual multi-armed bandit (MAB) is a widely used framework for problems requiring sequential decision-making under uncertainty, such as recommendation systems. In applications involving a large number of users, the performance of contextual MAB can be significantly improved by facilitating collaboration among multiple users. This has been achieved by the clustering of bandits (CB) methods, which adaptively group the users into different clusters and achieve collaboration by allowing the users in the same cluster to share data. However, classical CB algorithms typically rely on numerical reward feedback, which may not be practical in certain real-world applications. For instance, in recommendation systems, it is more realistic and reliable to solicit preference feedback between pairs of recommended items rather than absolute rewards. To address this limitation, we introduce the first "clustering of dueling bandit algorithms" to enable collaborative decision-making based on preference feedback. We propose two novel algorithms: (1) Clustering of Linear Dueling Bandits (COLDB) which models the user reward functions as linear functions of the context vectors, and (2) Clustering of Neural Dueling Bandits (CONDB) which uses a neural network to model complex, non-linear user reward functions. Both algorithms are supported by rigorous theoretical analyses, demonstrating that user collaboration leads to improved regret bounds. Extensive empirical evaluations on synthetic and real-world datasets further validate the effectiveness of our methods, establishing their potential in real-world applications involving multiple users with preference-based feedback.

Refining Adaptive Zeroth-Order Optimization at Ease

Recently, zeroth-order (ZO) optimization plays an essential role in scenarios where gradient information is inaccessible or unaffordable, such as black-box systems and resource-constrained environments. While existing adaptive methods such as ZO-AdaMM have shown promise, they are fundamentally limited by their underutilization of moment information during optimization, usually resulting in underperforming convergence. To overcome these limitations, this paper introduces Refined Adaptive Zeroth-Order Optimization (R-AdaZO). Specifically, we first show the untapped variance reduction effect of first moment estimate on ZO gradient estimation, which improves the accuracy and stability of ZO updates. We then refine the second moment estimate based on these variance-reduced gradient estimates to better capture the geometry of the optimization landscape, enabling a more effective scaling of ZO updates. We present rigorous theoretical analysis to show (I) the first analysis to the variance reduction of first moment estimate in ZO optimization, (II) the improved second moment estimates with a more accurate approximation of its variance-free ideal, (III) the first variance-aware convergence framework for adaptive ZO methods, which may be of independent interest, and (IV) the faster convergence of R-AdaZO than existing baselines like ZO-AdaMM. Our extensive experiments, including synthetic problems, black-box adversarial attack, and memory-efficient fine-tuning of large language models (LLMs), further verify the superior convergence of R-AdaZO, indicating that R-AdaZO offers an improved solution for real-world ZO optimization challenges.