AI-Assisted Code Review as a Scaffold for Code Quality and Self-Regulated Learning: An Experience Report

Code review is central to software engineering education but hard to scale in capstone projects due to tight deadlines, uneven peer feedback, and limited prior experience. We investigate an LLM-as-reviewer integrated directly into GitHub pull requests (human-in-the-loop) across two cohorts (more than 100 students, 2023--2024). Using a mixed-methods design -- GitHub data, reflective reports, and a targeted survey -- we examine engagement and responsiveness as behavioral indicators of self-regulated learning processes. Quantitatively, the 2024 cohort produced more iterative activity (1176 vs. 581 PRs), while technical issues observed in 2023 (227 failed AI attempts) dropped to zero after tool and instructional refinements. Despite different adoption levels (93\% vs. 50\% of teams using the tool), responsiveness was stable: 32\% (2023) and 33\% (2024) of successfully AI-reviewed PRs were followed by subsequent commits on the same PR. Qualitatively, students used the LLM's structured comments to focus reviews and discuss code quality, while guidance reduced over-reliance. We contribute: (i) an in-workflow design for an AI reviewer that scaffolds learning while mitigating cognitive offloading; (ii) a repeated cross sectional comparison across two cohorts in authentic settings; (iii) a mixed-methods analysis combining objective GitHub metrics with student self-reports; and (iv) evidence-based pedagogical recommendations for responsible, student-led AI-assisted review.

Birds of a Feather Cluster Nearby: a Proximity-Aware Geo-Codebook for Local Service Recommendation

Generative recommendation systems are increasingly adopted in local service platforms, where semantic relevance alone is insufficient without strict geographic feasibility. A key technical challenge lies in semantic ID (SID) tokenization, which directly impacts the recommendation performance. However, existing semantic codebooks neglect geographic constraints, often resulting in recommendations that are semantically relevant yet geographically unreachable. To address this limitation, we propose Pro-GEO, a Proximity-aware GEO-codebook. Pro-GEO establishes a geo-centroid local coordinate system to capture intra-cluster spatial relationships and a geo-rotary position encoding mechanism that models geographic proximity as orthogonal rotational transformations in the high-dimensional embedding. This design enables semantic and spatial signals to be jointly modeled in a balanced manner, without reducing geographic information to a weak auxiliary feature. Extensive experiments conducted on a large-scale industrial dataset reveal that Pro-GEO significantly outperforms state-of-the-art methods. In particular, Pro-GEO reduces the average geographic clustering distance by 45.60% and achieves a 1.87% improvement in Hit@50, highlighting its effectiveness for real-world local service recommendation.

Code Broker: A Multi-Agent System for Automated Code Quality Assessment

We present Code Broker, a multi agent system built with Google Agent Development Kit ADK that analyses Python code from files, local directories, or GitHub repositories and generates actionable quality assessment reports. The system employs a hierarchical five agents architecture in which a root orchestrator coordinates a sequential pipeline agent, which in turn dispatches three specialised agents in parallel a Correctness Assessor, a Style Assessor, and a Description Generator before synthesising findings through an Improvement Recommender. Reports score four dimensions correctness, security, style, and maintainability and are rendered in both Markdown and HTML. Code Broker combines LLM based reasoning with deterministic static-analysis signals from Pylint, uses asynchronous execution with retry logic to improve robustness, and explores lightweight session memory for retaining and querying prior assessment context. We position the paper as a technical report on system design and prompt or tool orchestration, and present a preliminary qualitative evaluation on representative Python codebases. The results suggest that parallel specialised agents produce readable, developer oriented feedback, while also highlighting current limitations in evaluation depth, security tooling, large repository handling, and the current use of only in memory persistence. All code and reproducibility materials are available at: https://github.com/Samir-atra/agents_intensive_dev.

Adopting State-of-the-Art Pretrained Audio Representations for Music Recommender Systems

Over the years, Music Information Retrieval (MIR) research community has released various models pretrained on large amounts of music data. Transfer learning showcases the proven effectiveness of pretrained backend models for a broad spectrum of downstream tasks, including auto-tagging and genre classification. However, MIR papers generally do not explore the efficiency of pretrained models for Music Recommender Systems (MRS). In addition, the Recommender Systems community tends to favour traditional end-to-end neural network training. Our research addresses this gap and evaluates the performance of nine pretrained backend models (MusicFM, Music2Vec, MERT, EncodecMAE, Jukebox, MusiCNN, MULE, MuQ and MuQ-MuLan) in the context of MRS. We assess them using five recommendation approaches: K-Nearest Neighbours (KNN), Shallow Neural Network, Contrastive Multi-Modal projection, a Hybrid model, and BERT4Rec both for the hot and cold-start scenarios. Our findings suggest that pretrained audio representations exhibit significant performance disparity between traditional MIR tasks and both hot and cold music recommendations, indicating that valuable aspects of musical information captured by backend models may differ depending on the task. This study establishes a foundation for further exploration of pretrained audio representations to enhance music recommendation systems.

Don't Make the LLM Read the Graph: Make the Graph Think

We investigate whether explicit belief graphs improve LLM performance in cooperative multi-agent reasoning. Through 3,000+ controlled trials across four LLM families in the cooperative card game Hanabi, we establish four findings. First, integration architecture determines whether belief graphs provide value: as prompt context, graphs are decorative for strong models and beneficial only for weak models on 2nd-order Theory of Mind (80% vs 10%, p<0.0001, OR=36.0); when graphs gate action selection through ranked shortlists, they become structurally essential even for strong models (100% vs 20% on 2nd-order ToM, p<0.001). Second, we identify "Planner Defiance," a model-family-specific failure where LLMs override correct planner recommendations at partial competence (90% override, replicated N=20); Gemini models show near-zero defiance while Llama 70B shows 90%, and models distinguish factual context (deferred to) from advisory recommendations (overridden). Third, full-game evidence confirms inter-agent conventions (+128% over baseline, p=0.003) outperform all single-agent interventions, and individual belief-graph components must be combined to produce gains. Fourth, preliminary scaling analysis (N=10/cell, exploratory) suggests graph depth has diminishing returns: shallow graphs provide the best cost-benefit ratio, while deeper ToM graphs appear harmful at larger player counts (-1.5 pts at 5-player, p=0.029).

CASP: Support-Aware Offline Policy Selection for Two-Stage Recommender Systems

Two-stage recommender systems first choose a candidate generator and then rank items within the generated set. Because the generator decides which items are available to the ranker, changing the generator changes both the policy value and the data support used to estimate that value. This creates an offline selection problem that standard single-stage objectives do not capture: a policy may look good under a retrieval score or a raw off-policy value estimate, but still be unreliable if it depends on weakly supported generator-item pairs. We propose CASP (Coupled Action-Set Pessimism), a support-aware offline selector for finite libraries of two-stage recommender policies. CASP combines doubly robust value estimation with a support-burden penalty. We show that stagewise rules that ignore downstream continuation value can be arbitrarily suboptimal, and we derive population, finite-class, and reconstructed-propensity guarantees for conservative selection. In simulations and a reconstructed MovieLens 1M application, CASP selects lower-burden policies when estimated value and support credibility are in tension.

Learning Evidence Highlighting for Frozen LLMs

Large Language Models (LLMs) can reason well, yet often miss decisive evidence when it is buried in long, noisy contexts. We introduce HiLight, an Evidence Emphasis framework that decouples evidence selection from reasoning for frozen LLM solvers. HiLight avoids compressing or rewriting the input, which can discard or distort evidence, by training a lightweight Emphasis Actor to insert minimal highlight tags around pivotal spans in the unaltered context. A frozen Solver then performs downstream reasoning on the emphasized input. We cast highlighting as a weakly supervised decision-making problem and optimize the Actor with reinforcement learning using only the Solver's task reward, requiring no evidence labels and no access to or modification of the Solver. Across sequential recommendation and long-context question answering, HiLight consistently improves performance over strong prompt-based and automated prompt-optimization baselines. The learned emphasis policy transfers zero-shot to both smaller and larger unseen Solver families, including an API-based Solver, suggesting that the Actor captures genuine, reusable evidence structure rather than overfitting to a single backbone.

ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning

Graph filter design is central to spectral collaborative filtering, yet most existing methods rely on manually tuned hyperparameters rather than fully learnable filters. We show that this challenge stems from a bias in traditional recommendation objectives, which induces a spectral phenomenon termed low-frequency explosion, thereby fundamentally hindering the effective learning of graph filters. To overcome this limitation, we propose a novel adaptive spectral graph collaborative filtering framework (ASPIRE) based on a bi-level optimization objective. Guided by our theoretical analysis, we disentangle the filter learning objective, which in turn leads to excellent recommendation performance, spectral adaptivity, and training stability in practice. Extensive experiments show our learned filters match the performance of carefully engineered task-specific designs. Furthermore, ASPIRE is equally effective in LLM-powered collaborative filtering. Our findings demonstrate that graph filter learning is viable and generalizable, paving the way for more expressive graph neural networks in collaborative filtering.

Objective Shaping with Hard Negatives: Windowed Partial AUC Optimization for RL-based LLM Recommenders

Reinforcement learning (RL) effectively optimizes Large Language Model (LLM)-based recommenders by contrasting positive and negative items. Empirically, training with beam-search negatives consistently outperforms random negatives, yet the mechanism is not well understood. We address this gap by analyzing the induced optimization objective and show that: (i) Under binary reward feedback, optimizing LLM recommenders with Group Relative Policy Optimization (GRPO) is theoretically equivalent to maximizing the Area Under the ROC Curve (AUC), which is often misaligned with Top-$K$ recommendation; and (ii) Replacing random negatives with beam-search negatives reshapes the objective toward partial AUC, improving alignment with Top-$K$ metrics. Motivated by this perspective, we introduce Windowed Partial AUC (WPAUC), which constrains the false positive rate (FPR) to a window [$α,α+d$] to more directly align with Top-$K$ metrics. We further propose an efficient Threshold-Adjusted Windowed reweighting (TAWin) RL method for its optimization, enabling explicit control over the targeted Top-$K$ performance. Experiments on four real-world datasets validate the theory and deliver consistent state-of-the-art performance.

Tell Me Why: Designing an Explainable LLM-based Dialogue System for Student Problem Behavior Diagnosis

Diagnosing student problem behaviors requires teachers to synthesize multifaceted information, identify behavioral categories, and plan intervention strategies. Although fine-tuned large language models (LLMs) can support this process through multi-turn dialogue, they rarely explain why a strategy is recommended, limiting transparency and teachers' trust. To address this issue, we present an explainable dialogue system built on a fine-tuned LLM. The system uses a hierarchical attribution method based on explainable AI (xAI) to identify dialogue evidence for each recommendation and generate a natural-language explanation based on that evidence. In technical evaluation, the method outperformed baseline approaches in identifying supporting evidence. In a preliminary user study with 22 pre-service teachers, participants who received explanations reported higher trust in the system. These findings suggest a promising direction for improving LLM explainability in educational dialogue systems.