Preventing unexpected long-latency spikes is crucial for latency-sensitive hardware systems like Solid-State Drives (SSDs). Conventional test case (TC) generation methods often lack reproducibility and rely on proprietary internal firmware knowledge, limiting their applicability. To address this, we propose SNIFFER, a vendor-agnostic, black-box framework that utilizes Reinforcement Learning (RL) for the automated generation of latency anomaly-inducing TCs. SNIFFER interacts directly with real SSD hardware, using only externally observable metrics from standardized tools like Flexible I/O and Open Compute Project. Our framework formulates the problem as a sequential decision-making process, enabling an RL agent to learn complex I/O patterns that induce stress. We demonstrate that SNIFFER consistently generates effective TCs, inducing up to 74.7% higher maximum latency in up to 85% fewer steps compared to a random baseline. More importantly, we demonstrate its superiority over alternative black-box optimization methods, such as Genetic Algorithms, validating our approach for non-stationary hardware environments. SNIFFER ’s ability to reproducibly generate diverse and stressful TCs makes it a powerful tool for automated industrial validation pipelines.

Recent advances in neural network architectures, such as the Transformer, have enabled a shift from task-specific models to unified foundation models, significantly enhancing generalization and scalability. In contrast, analog circuit design has traditionally relied on bespoke optimization models tailored to individual circuits. To address this gap, we propose M3, a novel unified reinforcement learning (RL) that concurrently optimizes multiple circuits with different topologies to meet target specifications, without requiring task-specific adjustments. The M3 framework employs the Mamba architecture, a recently emerging model regarded as a potential alternative to the Transformer. It combines model-based RL with a dynamic scheduling mechanism that adapts RL parameters to balance exploration (seeking novel designs) and exploitation (refining existing ones). Experimental results demonstrate that M3 successfully trains RL agents capable of simultaneously optimizing multiple circuits, having different topologies, to achieve target performance levels while prior RL-based methods are unable to do. This approach highlights the potential of developing a unified model for optimizing circuits across varying topologies and target specifications1.

Graph Transformers (GTs) have emerged as a powerful alternative to message-passing neural networks, yet their performance heavily depends on effectively embedding structural inductive biases. In this work, we introduce novel structural encodings (SEs) grounded in a rigorous analysis of random walks (RWs), leveraging Green and Martin kernels that we have carefully redefined for AI applications while preserving their mathematical essence.These kernels capture the long-term behavior of RWs on graphs and allow for enhanced representation of complex topologies, including non-aperiodic and directed acyclic substructures.Empirical evaluations across eight benchmark datasets demonstrate strong performance across diverse tasks, notably in molecular and circuit domains.We attribute this performance boost to the improved ability of our kernel-based SEs to encode intricate structural information, thereby strengthening the global attention and inductive bias within GTs.This work highlights the effectiveness of theoretically grounded kernel methods in advancing Transformer-based models for graph learning.

Automation of analog circuit design is highly desirable, yet challenging. Various approaches such as deep reinforcement learning (DRL), genetic algorithms, and Bayesian optimization have been proposed and found to be effective. However, these techniques require a large number of interactions with a real simulator, leading to high computational costs. Therefore, we present a novel DRL method, CRONuS, for automatic analog circuit design that uses a surrogate for the simulator. With the help of the surrogate, our method is capable of augmenting a data set with a conservative reward design for stable policy training, without having to interact with the simulator. Regardless of the type of analog circuit, our experiment demonstrated a more than 5 × improvement in sample efficiency with varying target performance metrics.

Well-designed test cases (TCs) are crucial for en-suring the quality of Solid-State Drive (SSD) products. Indeed, validating SSD firmware code by the TCs is indispensable to check if there are no defects during the SSD development process. Accordingly, it is necessary to create short TCs covering firmware code as much as possible for efficient and precise validation. While various methods are available for generating TCs, existing automated approaches overlook backward compatibility, a key property in the SSD development process. To utilize the property, we introduce a novel deep-learning approach called GRAFT, which combines graph representation learning and reinforcement learning (RL) for automated TC generation in SSDs by leveraging pre-collected data. G RAFT trains a graph neural network to extract the underlying structure of the SSD firmware code from a given SSD simulator. The resulting graph embeddings serve as observations in the RL process. To address the challenge of over- estimation in an external domain in the RL process, conservative Q-Iearning, an offline RL technique, is employed using the pre- collected data. Despite the limitation of not being able to interact with the SSD simulator for training, we demonstrate that GRAFT successfully trains RL agents that generate TCs. The TCs are not only significantly more efficient with 3.5x shorter than randomly generated TCs by a black-box fuzzer but also exhibit comparable coverage and efficiency to those created by human experts with domain knowledge, which fully took three days. Moreover, the TCs achieves maximum coverage more reliably than any other methods in the experiments.

BACKGROUND: Recently, the metabolite-likeness of the drug space has emerged and has opened a new possibility for exploring human metabolite-like candidates in drug discovery. However, the applicability of metabolite-likeness in drug discovery has been largely unexplored. Moreover, there are no reports on its applications for the repositioning of drugs to possible enzyme modulators, although enzyme-drug relations could be directly inferred from the similarity relationships between enzyme's metabolites and drugs. METHODS: We constructed a drug-metabolite structural similarity matrix, which contains 1,861 FDA-approved drugs and 1,110 human intermediary metabolites scored with the Tanimoto similarity. To verify the metabolite-likeness measure for drug repositioning, we analyzed 17 known antimetabolite drugs that resemble the innate metabolites of their eleven target enzymes as the gold standard positives. Highly scored drugs were selected as possible modulators of enzymes for their corresponding metabolites. Then, we assessed the performance of metabolite-likeness with a receiver operating characteristic analysis and compared it with other drug-target prediction methods. We set the similarity threshold for drug repositioning candidates of new enzyme modulators based on maximization of the Youden's index. We also carried out literature surveys for supporting the drug repositioning results based on the metabolite-likeness. RESULTS: In this paper, we applied metabolite-likeness to repurpose FDA-approved drugs to disease-associated enzyme modulators that resemble human innate metabolites. All antimetabolite drugs were mapped with their known 11 target enzymes with statistically significant similarity values to the corresponding metabolites. The comparison with other drug-target prediction methods showed the higher performance of metabolite-likeness for predicting enzyme modulators. After that, the drugs scored higher than similarity score of 0.654 were selected as possible modulators of enzymes for their corresponding metabolites. In addition, we showed that drug repositioning results of 10 enzymes were concordant with the literature evidence. CONCLUSIONS: This study introduced a method to predict the repositioning of known drugs to possible modulators of disease associated enzymes using human metabolite-likeness. We demonstrated that this approach works correctly with known antimetabolite drugs and showed that the proposed method has better performance compared to other drug target prediction methods in terms of enzyme modulators prediction. This study as a proof-of-concept showed how to apply metabolite-likeness to drug repositioning as well as potential in further expansion as we acquire more disease associated metabolite-target protein relations.