The increasing use of complex machine learning models in education has led to concerns about their interpretability, which in turn has spurred interest in developing explainability techniques that are both faithful to the model's inner workings and intelligible to human end-users. In this paper, we describe a novel approach to creating a neural-network-based behavior detection model that is interpretable by design. Our model is fully interpretable, meaning that the parameters we extract for our explanations have a clear interpretation, fully capture the model's learned knowledge about the learner behavior of interest, and can be used to create explanations that are both faithful and intelligible. We achieve this by implementing a series of constraints to the model that both simplify its inference process and bring it closer to a human conception of the task at hand. We train the model to detect gaming-the-system behavior, evaluate its performance on this task, and compare its learned patterns to those identified by human experts. Our results show that the model is successfully able to learn patterns indicative of gaming-the-system behavior while providing evidence for fully interpretable explanations. We discuss the implications of our approach and suggest ways to evaluate explainability using a human-grounded approach.

Large Reasoning Models (LRMs) have the ability to self-correct even when they make mistakes in their reasoning paths. However, our study reveals that when the reasoning process starts with a short but poor beginning, it becomes difficult for the model to recover. We refer to this phenomenon as the "Prefix Dominance Trap". Inspired by psychological findings that peer interaction can promote self-correction without negatively impacting already accurate individuals, we propose **Learning from Peers** (LeaP) to address this phenomenon. Specifically, every tokens, each reasoning path summarizes its intermediate reasoning and shares it with others through a routing mechanism, enabling paths to incorporate peer insights during inference. However, we observe that smaller models sometimes fail to follow summarization and reflection instructions effectively. To address this, we fine-tune them into our **LeaP-T** model series. Experiments on AIME 2024, AIME 2025, AIMO 2025, and GPQA Diamond show that LeaP provides substantial improvements. For instance, QwQ-32B with LeaP achieves nearly 5 absolute points higher than the baseline on average, and surpasses DeepSeek-R1-671B on three math benchmarks with an average gain of 3.3 points. Notably, our fine-tuned LeaP-T-7B matches the performance of DeepSeek-R1-Distill-Qwen-14B on AIME 2024. In-depth analysis reveals LeaP's robust error correction by timely peer insights, showing strong error tolerance and handling varied task difficulty. LeaP marks a milestone by enabling LRMs to collaborate during reasoning. Our code, datasets, and models are available at https://learning-from-peers.github.io/ .

We introduce MLE-Dojo, a Gym-style framework for systematically reinforcement learning, evaluating, and improving autonomous large language model (LLM) agents in iterative machine learning engineering (MLE) workflows. Unlike existing benchmarks that primarily rely on static datasets or single-attempt evaluations, MLE-Dojo provides an interactive environment enabling agents to iteratively experiment, debug, and refine solutions through structured feedback loops. Built upon 200+ real-world Kaggle challenges, MLE-Dojo covers diverse, open-ended MLE tasks carefully curated to reflect realistic engineering scenarios such as data processing, architecture search, hyperparameter tuning, and code debugging. Its fully executable environment supports comprehensive agent training via both supervised fine-tuning and reinforcement learning, facilitating iterative experimentation, realistic data sampling, and real-time outcome verification. Extensive evaluations of eight frontier LLMs reveal that while current models achieve meaningful iterative improvements, they still exhibit significant limitations in autonomously generating long-horizon solutions and efficiently resolving complex errors. Furthermore, MLE-Dojo's flexible and extensible architecture seamlessly integrates diverse data sources, tools, and evaluation protocols, uniquely enabling model-based agent tuning and promoting interoperability, scalability, and reproducibility. We open-source our framework and benchmarks to foster community-driven innovation towards next-generation MLE agents.

Persuasion is a fundamental aspect of communication, influencing decision-making across diverse contexts, from everyday conversations to high-stakes scenarios such as politics, marketing, and law. The rise of conversational AI systems has significantly expanded the scope of persuasion, introducing both opportunities and risks. AI-driven persuasion can be leveraged for beneficial applications, but also poses threats through manipulation and unethical influence. Moreover, AI systems are not only persuaders, but also susceptible to persuasion, making them vulnerable to adversarial attacks and bias reinforcement. Despite rapid advancements in AI-generated persuasive content, our understanding of what makes persuasion effective remains limited due to its inherently subjective and context-dependent nature. In this survey, we provide a comprehensive overview of computational persuasion, structured around three key perspectives: (1) AI as a Persuader, which explores AI-generated persuasive content and its applications; (2) AI as a Persuadee, which examines AI's susceptibility to influence and manipulation; and (3) AI as a Persuasion Judge, which analyzes AI's role in evaluating persuasive strategies, detecting manipulation, and ensuring ethical persuasion. We introduce a taxonomy for computational persuasion research and discuss key challenges, including evaluating persuasiveness, mitigating manipulative persuasion, and developing responsible AI-driven persuasive systems. Our survey outlines future research directions to enhance the safety, fairness, and effectiveness of AI-powered persuasion while addressing the risks posed by increasingly capable language models.

Emotion-Gradient Metacognitive RSI (Part I): Theoretical Foundations and Single-Agent Architecture Rintaro Ando The University of Tokyo, Graduate School of Public Policy Abstract We present the Emotion-Gradient Metacognitive Recursive Self-Improvement (EG-MRSI) framework, a novel architecture that integrates introspective metacognition, emotion-based intrinsic motivation, and recursive self-modification into a unified theoretical system. The framework is explicitly capable of overwriting its own learning algorithm under formally bounded risk. Building upon the Noise-to-Meaning RSI (N2M-RSI) foundation, EG-MRSI introduces a differentiable intrinsic reward function driven by confidence, error, novelty, and cumulative success. This signal regulates both a metacognitive mapping and a self-modification operator constrained by provable safety mechanisms. We formally define the initial agent configuration, emotion gradient dynamics, and RSI trigger conditions, and derive a reinforcement-compatible optimization objective that guides the agent's development trajectory. Meaning Density and Meaning-Conversion Efficiency are introduced as quantifiable metrics of semantic learning, closing the gap between internal structure and predictive informativeness. This Part I paper establishes the single-agent theoretical foundations of EG-MRSI. Future parts will extend this framework to include safety certificates and rollback protocols (Part II), collective intelligence mechanisms (Part III), and feasibility constraints including thermodynamic and computational limits (Part IV). Together, the EG-MRSI series provides a rigorous, extensible foundation for open-ended and safe AGI. 1 Introduction The quest for artificial general intelligence (AGI) has long been accompanied by the challenge of recursive self-improvement (RSI): the ability of an agent to modify its own structure and thereby increase its capabilities over time. Recent progress in large-scale language models has reignited the classical vision of the ultra-intelligent machine-- a system capable of recursively enhancing its own capabilities until human intelligence is rapidly outstripped [Good, 1965, Schmidhuber, 2003, Yudkowsky, 2008, Goertzel, 2014, Yampolskiy, 2015]. While the classical vision of RSI promises rapid leaps in intelligence, it also raises profound safety, control, and alignment issues.

The broad availability of generative AI offers new opportunities to support various work domains, including agile software development. Agile epics are a key artifact for product managers to communicate requirements to stakeholders. However, in practice, they are often poorly defined, leading to churn, delivery delays, and cost overruns. In this industry case study, we investigate opportunities for large language models (LLMs) to evaluate agile epic quality in a global company. Results from a user study with 17 product managers indicate how LLM evaluations could be integrated into their work practices, including perceived values and usage in improving their epics. High levels of satisfaction indicate that agile epics are a new, viable application of AI evaluations. However, our findings also outline challenges, limitations, and adoption barriers that can inform both practitioners and researchers on the integration of such evaluations into future agile work practices.

Instruction following evaluates large language models (LLMs) on their ability to generate outputs that adhere to user-defined constraints. However, existing benchmarks often rely on templated constraint prompts, which lack the diversity of real-world usage and limit fine-grained performance assessment. To fill this gap, we propose a multi-dimensional constraint framework encompassing three constraint patterns, four constraint categories, and four difficulty levels. Building on this framework, we develop an automated instruction generation pipeline that performs constraint expansion, conflict detection, and instruction rewriting, yielding 1,200 code-verifiable instruction-following test samples. We evaluate 19 LLMs across seven model families and uncover substantial variation in performance across constraint forms. For instance, average performance drops from 77.67% at Level I to 32.96% at Level IV. Furthermore, we demonstrate the utility of our approach by using it to generate data for reinforcement learning, achieving substantial gains in instruction following without degrading general performance. In-depth analysis indicates that these gains stem primarily from modifications in the model's attention modules parameters, which enhance constraint recognition and adherence. Code and data are available in https://github.com/Junjie-Ye/MulDimIF.

Instruction tuning has emerged as a critical paradigm for improving the capabilities and alignment of large language models (LLMs). However, existing iterative model-aware data selection methods incur significant computational overhead, as they rely on repeatedly performing full-dataset model inference to estimate sample utility for subsequent training iterations, creating a fundamental efficiency bottleneck. In this paper, we propose LEAD, an efficient iterative data selection framework that accurately estimates sample utility entirely within the standard training loop, eliminating the need for costly additional model inference. At its core, LEAD introduces Instance-Level Dynamic Uncertainty (IDU), a theoretically grounded utility function combining instantaneous training loss, gradient-based approximation of loss changes, and exponential smoothing of historical loss signals. To further scale efficiently to large datasets, LEAD employs a two-stage, coarse-to-fine selection strategy, adaptively prioritizing informative clusters through a multi-armed bandit mechanism, followed by precise fine-grained selection of high-utility samples using IDU. Extensive experiments across four diverse benchmarks show that LEAD significantly outperforms state-of-the-art methods, improving average model performance by 6.1%-10.8% while using only 2.5% of the training data and reducing overall training time by 5-10x.

Transforming educational technologies through the integration of large language models (LLMs) and virtual reality (VR) offers the potential for immersive and interactive learning experiences. However, the effects of LLMs on user engagement and attention in educational environments remain open questions. In this study, we utilized a fully LLM-driven virtual learning environment, where peers and teachers were LLM-driven, to examine how students behaved in such settings. Specifically, we investigate how peer question-asking behaviors influenced student engagement, attention, cognitive load, and learning outcomes and found that, in conditions where LLM-driven peer learners asked questions, students exhibited more targeted visual scanpaths, with their attention directed toward the learning content, particularly in complex subjects. Our results suggest that peer questions did not introduce extraneous cognitive load directly, as the cognitive load is strongly correlated with increased attention to the learning material. Considering these findings, we provide design recommendations for optimizing VR learning spaces.

Recently, there has been growing interest in collecting reasoning-intensive pretraining data to improve LLMs' complex reasoning ability. Prior approaches typically rely on supervised classifiers to identify such data, which requires labeling by humans or LLMs, often introducing domain-specific biases. Due to the attention heads being crucial to in-context reasoning, we propose AttentionInfluence, a simple yet effective, training-free method without supervision signal. Our approach enables a small pretrained language model to act as a strong data selector through a simple attention head masking operation. Specifically, we identify retrieval heads and compute the loss difference when masking these heads. We apply AttentionInfluence to a 1.3B-parameter dense model to conduct data selection on the SmolLM corpus of 241B tokens, and mix the SmolLM corpus with the selected subset comprising 73B tokens to pretrain a 7B-parameter dense model using 1T training tokens and WSD learning rate scheduling. Our experimental results demonstrate substantial improvements, ranging from 1.4pp to 3.5pp, across several knowledge-intensive and reasoning-heavy benchmarks (i.e., MMLU, MMLU-Pro, AGIEval-en, GSM8K, and HumanEval). This demonstrates an effective weak-to-strong scaling property, with small models improving the final performance of larger models-offering a promising and scalable path for reasoning-centric data selection.