This paper introduces the Functionality-Driven Multi-Agent Group Relative Policy Optimization (FD-MAGRPO) algorithm, which is designed to enhance exploration efficiency in reinforcement learning (RL) for analog integrated circuit sizing. Our proposed method integrates two key innovations: (1) a critic-free multi-agent optimization framework based on Group Relative Policy Optimization (GRPO), that eliminates the critic network and achieves stable and efficient policy updates; and (2) a functionality-driven grouping strategy, that enables agents to coordinate exploration by functional roles instead of circuit blocks, thereby improving credit assignment and cooperation. Experimental results on practical low-dropout regulator (LDO) circuits with 65–179 design parameters show that the proposed method achieves rapid convergence with only 800–3000 simulations, yielding a 4.8×–13.0× speedup over state-of-the-art methods. Mathematical analysis and empirical studies validate that the combination of critic-free optimization and functionality-based grouping leads to higher exploration efficiency and faster convergence. The proposed method enables the discovery of higher circuit performances that are inaccessible to conventional approaches, establishing FD-MAGRPO as a robust and efficient solution for complex analog-LDO sizing tasks.

Migrating a validated analog layout across technology nodes remains labor-intensive. Recent automatic migration methods often miss multi-level design intent embedded in expert layouts and may suffer from routing-induced LVS violations and unstable placement behaviors. We present GRAIN, a design-intent-driven analog layout migration framework that performs constraint-aware hierarchical placement migration to preserve multi-level placement behaviors, and uses guide-based routing that decouples similarity from legality via a maze router to reliably produce LVS-clean layouts. Experiments on real designs migrated from 65 nm to 40 nm and 28 nm show that, compared to a recent representative analog layout migration framework, GRAIN delivers 100% LVS-clean layouts without manual fixes and reduces area and wirelength by 13.8% and 29.2% on average, while also yielding post-layout metrics closer to the schematic.

Analog circuit sizing remains a critical bottleneck in integrated circuit design, requiring extensive manual effort and computational resources. While multi-agent reinforcement learning (MARL) accelerates optimization through parallel agent training, existing approaches rely on manual circuit block clustering that fails to capture functional relationships between parameters. This paper presents ACEMARL, an adaptive clustering framework that automatically discovers functionally similar parameter clusters. ACEMARL integrates Bi-population Covariance Matrix Adaptation Evolution Strategy (BIPOP-CMA-ES), a high-performance evolutionary algorithm, for multi-modal exploration with data-driven clustering, aiming for automatic agent assignment. Experimental validation on amplifier and low-dropout regulators with up to 179 parameters demonstrated 3.3-5.0× faster convergence and 5.7-38.5% Figure-of-Merit (FoM) improvement compared to state-of-the-art (SOTA) block-based methods. The framework reduced confidence interval width by 31.6-60.7% along mean reward trajectories, enabling fully automated analog circuit sizing with improved stability and performance.

Large Language Models (LLMs) hold significant potential for transforming computer science education, yet concerns over their possible negative effects on student learning and retention have slowed broader instructor adoption. Evidence on LLM use is mixed. While novices may benefit from the generative capabilities of AI, they also risk developing overreliance. To address these concerns, we investigate how the pace of interaction with AI assistants affects learning in introductory CS courses by deploying three AI assistants (Fast, Medium, and Slow) in a classroom setting. Our results show that the slower-paced, Socratic-style AI assistant significantly increases learning, especially for students with less prior knowledge. Although faster-paced interaction benefits more advanced students initially, learning retention degrades enough to negate those gains. Surprisingly, the medium-paced assistant with typical instructor preprompt elements shows no statistically significant improvements. Given that students may use fast-paced commercial AI tools for coursework regardless of policy, offering a slower-paced, Socratic-style AI alternative could meaningfully improve overall student learning outcomes.

Federated Learning (FL) has emerged as a promising privacy-preserving collaborative model training paradigm without sharing raw data. However, recent studies have revealed that private information can still be leaked through shared gradient information and attacked by Gradient Inversion Attacks (GIA). While many GIA methods have been proposed, a detailed analysis, evaluation, and summary of these methods are still lacking. Although various survey papers summarize existing privacy attacks in FL, few studies have conducted extensive experiments to unveil the effectiveness of GIA and their associated limiting factors in this context. To fill this gap, we first undertake a systematic review of GIA and categorize existing methods into three types, i.e., optimization-based GIA (OP-GIA), generation-based GIA (GEN-GIA), and analytics-based GIA (ANA-GIA). Then, we comprehensively analyze and evaluate the three types of GIA in FL, providing insights into the factors that influence their performance, practicality, and potential threats. Our findings indicate that OP-GIA is the most practical attack setting despite its unsatisfactory performance, while GEN-GIA has many dependencies and ANA-GIA is easily detectable, making them both impractical. Finally, we offer a three-stage defense pipeline to users when designing FL frameworks and protocols for better privacy protection and share some future research directions from the perspectives of attackers and defenders that we believe should be pursued. We hope that our study can help researchers design more robust FL frameworks to defend against these attacks.