Many AI-based code assistants, particularly those powered by Large Language Models (LLMs), provide complete solutions, which can reduce active problem solving and limit incidental learning, the acquisition of knowledge as a byproduct of task engagement. Such learning requires active participation rather than passive acceptance of AI-generated answers, which might be incorrect. This study examines how incidental learning can be supported through guided interaction. We present LeetCoach, an LLM-assisted coding platform that applies a cognitive forcing strategy, prompting learners to reflect and take incremental steps instead of receiving full solutions. Using LeetCode-style questions, we conducted a pilot study with novice and advanced college programmers who completed tasks under assisted and unassisted conditions. Novices showed substantial post-test gains despite receiving AI guidance only during the intervention, suggesting that incidental exposure improved later performance. Advanced learners showed smaller gains. Across both groups, participants required fewer debugging attempts in the post-test compared to earlier stages, indicating improved debugging efficiency and algorithmic understanding. These findings provide early evidence that LLMs can be designed to promote indirect learning while shaping problem-solving strategies. This work offers a proof of concept for cognitively informed tutoring systems in computer science education and discusses implications for integrating LLMs to enhance both immediate outcomes and lasting skill development.

Boolean Matrix Factorization (BMF) is a widely used technique to model binary interaction data in applications such as recommender systems, bioinformatics, and pattern mining. It approximates a binary matrix as the Boolean product of two low-rank binary matrices, capturing latent structure while preserving interpretability. While most existing work on BMF focuses on centralized settings, in real-world scenarios data is often distributed across clients due to privacy concerns. Federated BMF addresses this by enabling collaborative learning without sharing raw data. However, existing federated factorization methods are designed for real-valued or non-negative data and are ill-suited for Boolean structures. These methods either fail to preserve binary constraints or rely on relaxations that produce approximate outputs without guarantees. We address this by proposing a federated BMF algorithm based on alternating optimization combined with a randomized block-coordinate strategy. Each subproblem is solved exactly via integer programming, and the algorithm does not require all clients to participate in every communication round. Experiments on benchmark datasets for cancer genomics and recommendation tasks show that our method outperforms existing baselines by achieving lower prediction and reconstruction errors.

Developing effective multi-agent systems (MASs) is critical for many applications requiring collaboration and coordination with humans. Despite the rapid advance of multi-agent deep reinforcement learning (MADRL) in cooperative MASs, one of the major challenges that remain is the simultaneous learning and interaction of independent agents in dynamic environments in the presence of stochastic rewards. State-of-the-art MADRL models struggle to perform well in Coordinated Multi-agent Object Transportation Problems (CMOTPs) wherein agents must coordinate with each other and learn from stochastic rewards. In contrast, humans often learn rapidly to adapt to non-stationary environments that require coordination among people. In this article, motivated by the demonstrated ability of cognitive models based on Instance-based Learning Theory (IBLT) to capture human decisions in many dynamic decision-making tasks, we propose three variants of multi-agent IBL models (MAIBLs). The idea of these MAIBL algorithms is to combine the cognitive mechanisms of IBLT and the techniques of MADRL models to deal with coordination MASs in stochastic environments from the perspective of independent learners. We demonstrate that the MAIBL models exhibit faster learning and achieve better coordination in a dynamic CMOTP task with various settings of stochastic rewards compared to current MADRL models. We discuss the benefits of integrating cognitive insights into MADRL models.

Recommending to a group of users is multifaceted as people naturally adapt to other members, and it may turn out that what they choose in a group does not fully match individual interests. Besides, it has been shown that the recommendation needs of groups go beyond the aggregation of individual preferences. In practice, it is much more difficult to predict group choices because users take into account the others' reactions and different users react to the group in different ways. Thus, in this research, we aim at exploiting an interactive and conversational approach to facilitate the group decision-making process where the complex trade-off between the satisfaction of an individual and the group as a whole typically occurs and needs to be resolved. To attain this goal, we investigate approaches that can access a group situation and autonomously learn an adaptive interaction in a specific condition of the group.

In this abstract, we discuss how long-term and discussion-generated preferences can be appropriately combined in supporting group decision making. We measure the quality of a group recommendation model by varying the importance given to these two types of preferences in different group scenarios, where the group setting may impact on user's behavior. The results of a simulation experiment illustrate that when users' preferences are not influenced by the group, the preference aggregation model should weigh more the long-term preferences. In contrast, when discussion-generated preferences tend either to align with each other or to diverge due to the group setting, it is beneficial to take into account more the discussion-generated preferences, which help to capture the newly arising interests of the users.

Most research on group recommender systems relies on the assumption that individuals have conflicting preferences; in order to generate group recommendations the system should identify a fair way of aggregating these preferences. Both empirical studies and theoretical frameworks have tried to identify the most effective preference aggregation techniques without coming to definite conclusions. In this paper, we propose to approach group recommendation from the group dynamics perspective and analyze the group decision making process for a particular task (in the travel domain). We observe several individual and group properties and correlate them to choice satisfaction. Supported by these initial results we therefore advocate for the development of new group recommendation techniques that consider group dynamics and support the full group decision making process.

In this position paper, we take the experimental approach of putting algorithms aside, and reflect on what recommenders would be for people if they were not tied to technology. By looking at some of the shortcomings that current recommenders have fallen into and discussing their limitations from a human point of view, we ask the question: if freed from all limitations, what should, and what could, RecSys be? We then turn to the idea that life itself is the best recommender system, and that people themselves are the query. By looking at how life brings people in contact with options that suit their needs or match their preferences, we hope to shed further light on what current RecSys could be doing better. Finally, we look at the forms that RecSys could take in the future. By formulating our vision beyond the reach of usual considerations and current limitations, including business models, algorithms, data sets, and evaluation methodologies, we attempt to arrive at fresh conclusions that may inspire the next steps taken by the community of researchers working on RecSys.

Nowadays, recommender systems are becoming popular since they help users alleviate the information overload problem by offering personalized recommendations. Most systems apply collaborative filtering to predict individual preferences based on opinions of like-minded people through their ratings on

Medium access control (MAC) protocols play a crucial role in energy-efficiency, latency reduction for sensor networks. Many research efforts have been made to reduce energy consumption and shorten delay in multi-hop WSNs. Although some existing MAC protocols are energy-efficient and are able to mitigate the end-to-end delivery latency, there are great potential for further improvements. In this paper, we propose a new MAC protocol by introducing a new Adaptive Scheduling (AS) period within which the node's active duration is made adaptive to variable traffic load and able to resiliently schedule data packets for transmission in the Sleep period. The algorithm is designated to schedule more data packets for transmission in bursty and high traffic loads, thus enabling rapid dissemination of data and reduction of the end-to-end delivery latency. While in the light traffic loads, nodes enters the Sleep mode, mitigating idle listening and saving energy. Experiment results show that the proposed protocol is a great advancement of some existing protocols on performance, especially with heavy traffic loads.