Large language models (LLMs) are increasingly used in scientific domains. While they can produce reasoning-like content via methods such as chain-of-thought prompting, these outputs are typically unstructured and informal, obscuring whether models truly understand the fundamental reasoning paradigms that underpin scientific inference. To address this, we introduce a novel task named Latent Reasoning Chain Extraction (ARCHE), in which models must decompose complex reasoning arguments into combinations of standard reasoning paradigms in the form of a Reasoning Logic Tree (RLT). In an RLT, all reasoning steps are explicitly categorized as one of three variants of Peirce’s fundamental inference modes: deduction, induction, or abduction. To facilitate this task, we release ARCHE Bench, a new benchmark derived from 70 Nature Communications articles, including more than 1,900 references and 38,000 viewpoints. We propose two logic-aware evaluation metrics: Entity Coverage (EC) for content completeness and Reasoning Edge Accuracy (REA) for step-by-step logical validity. Evaluations on 10 leading LLMs on ARCHE Bench reveal that models exhibit a trade-off between REA and EC, and none are yet able to extract a complete and standard reasoning chain. These findings highlight a substantial gap between the abilities of current reasoning models and the rigor required for scientific argumentation.

OBJECTIVE: Evaluate how RAG architecture, including corpus structure, retrieval strategy, and pipeline complexity, affects LLM-based medical problem solving and knowledge retrieval in sleep medicine. MATERIALS AND METHODS: We benchmarked four open-source LLMs (Llama-3-8B, Llama -3 -70B, Qwen 2.5-14B, and Qwen 2.5-235B) using a knowledge base of five sleep medicine textbooks. We compared performance across three dimensions: corpus structure (raw text vs table-of-contents aligned.), retrieval strategy (dense embedding vs hybrid sparse-dense), and pipeline complexity (baseline vs augmented). Evaluation metrics included board-style multiple choice question (MCQ) accuracy and clinical case vignette diagnostic ranking. RESULTS: RAG improved MCQ accuracy for all models. Llama-8B saw the largest gain of 10.6% (61.8% to 72.4%), while Qwen-235B reached 87.3%. In clinical cases, Llama-8B accuracy dropped by 7.1% when using raw text and dense retrieval due to context noise. This was corrected by using structured hybrid configurations. Hybrid retrieval consistently outperformed dense-only methods. Overall, structured corpora improved primary diagnosis accuracy by 6.1% on average, with Qwen-235B reaching a peak 10.2% increase. DISCUSSION: RAG effectiveness depends on the balance between model size and data structure. Large models handle uncurated text well, but smaller models are easily distracted by irrelevant data. Hybrid retrieval is necessary to maintain precision with specialized medical terms. A structured corpus paired with a baseline hybrid pipeline offers the best stability and speed for clinical use. CONCLUSION: Rigorous data curation and hybrid retrieval are as essential as model scale for deploying safe, guideline-compliant AI in sleep medicine.

Temporal Graph Neural Networks (TGNNs) have become indispensable for analyzing dynamic graphs in critical applications such as social networks, communication systems, and financial networks. However, the robustness of TGNNs against adversarial attacks, particularly sophisticated attacks that exploit the temporal dimension, remains a significant challenge. Existing attack methods for Spatio-Temporal Dynamic Graphs (STDGs) often rely on simplistic, easily detectable perturbations (e.g., random edge additions/deletions) and fail to strategically target the most influential nodes and edges for maximum impact. We introduce the High Impact Attack (HIA), a novel restricted black-box attack framework specifically designed to overcome these limitations and expose critical vulnerabilities in TGNNs. HIA leverages a data-driven surrogate model to identify structurally important nodes (central to network connectivity) and dynamically important nodes (critical for the graph's temporal evolution). It then employs a hybrid perturbation strategy, combining strategic edge injection (to create misleading connections) and targeted edge deletion (to disrupt essential pathways), maximizing TGNN performance degradation. Importantly, HIA minimizes the number of perturbations to enhance stealth, making it more challenging to detect. Comprehensive experiments on five real-world datasets and four representative TGNN architectures (TGN, JODIE, DySAT, and TGAT) demonstrate that HIA significantly reduces TGNN accuracy on the link prediction task, achieving up to a 35.55% decrease in Mean Reciprocal Rank (MRR) - a substantial improvement over state-of-the-art baselines. These results highlight fundamental vulnerabilities in current STDG models and underscore the urgent need for robust defenses that account for both structural and temporal dynamics. Code and Data are available at https://github.com/ryandhjeon/hia.

Distributed deep neural network training necessitates efficient GPU collective communications, which are inherently susceptible to deadlocks. GPU collective deadlocks arise easily in distributed deep learning applications when multiple collectives circularly wait for each other. GPU collective deadlocks pose a significant challenge to the correct functioning and efficiency of distributed deep learning, and no general effective solutions are currently available. Only in specific scenarios, ad-hoc methods, making an application invoke collectives in a consistent order across GPUs, can be used to prevent circular collective dependency and deadlocks.

Sharding blockchain networks face significant scalability challenges due to high frequencies of cross-shard transactions and uneven workload distributions among shards. To address these scalability issues, account migration offers a promising solution. However, existing migration solutions struggle with the high computational overhead and insufficient capture of complex transaction patterns. We propose AERO, a deep reinforcement learning framework to facilitate efficient account migration in sharding blockchains. AERO employs a prefix-based grouping strategy to enable group-level migration decisions and capture complex transaction patterns and relationships between accounts. We also implement a sharding blockchain system called AEROChain, which integrates AERO and aligns with the blockchain decentralization principle. Extensive evaluation with real Ethereum transaction data demonstrates that AERO improves the system throughput by 31.77% compared to existing solutions, effectively reducing cross-shard transactions and balancing shard workloads.

Blockchain sharding technology has been used to enhance the scalability of blockchain systems. As the number of shards increases, the high latency inherent in cross-shard transactions gradually becomes a bottleneck, hindering improvements in overall system efficiency. Therefore, reducing the latency of cross-shard transactions is significantly important. However, existing mechanisms for handling cross-shard transactions fail to minimize the latency of cross-shard transactions and have not fully used the bandwidth available within shards. In this paper, we introduce Presto, a protocol designed for the account-state-based blockchain, which reduces the latency of handling cross-shard transactions. Presto leverages the concept of optimistic pre-execution along with pending tree to optimize cross-shard transaction processing. Presto also employs predistribution of cross-shard transactions with Erasure Coding to efficiently utilize bandwidth resources. We have developed an prototype and conducted extensive experiments on a cloud platform. The evaluation results indicate that Presto surpasses existing solutions in terms of system throughput, transaction confirmation latency, and mempool queue size, demonstrating Presto's potential to significantly improve blockchain scalability and user experience.

Sharding provides an opportunity to overcome the inherent scalability challenges of the blockchain, which is the infrastructure for the next generation of the Web. In a sharding blockchain, the state is partitioned into smaller groups known as "shards." Since the states are placed on different shards, cross-shard transactions are inevitable, which is detrimental to the performance of the sharding blockchain. Existing solutions place states based on heuristic algorithms or redistribute states via graph-partitioning-based methods, which are either less effective or costly. In this paper, we present SPRING, the first deep-reinforcement-learning(DRL)-based sharding framework for state placement. SPRING formulates the state placement as a Markov Decision Process, which considers the cross-shard transaction ratio and workload balancing and employs DRL to learn the effective state placement policy. Experimental results based on real Ethereum transaction data demonstrate the superiority of SPRING compared to other state placement solutions. In particular, it decreases the cross-shard transaction ratio by up to 26.63% and boosts throughput by up to 36.03%, all without unduly sacrificing the workload balance among shards. Moreover, updating the training model and making decisions takes only 0.1s and 0.002s, respectively, which shows the overhead is acceptable.

In permissioned blockchains, the bandwidth of consensus nodes is mainly consumed by transaction ordering and block distribution; hence, the allocation of consensus nodes' bandwidth makes a significant difference to the system throughput. Previous research focuses on the consensus layer and attempts to optimize consensus protocols to improve throughput, which, however, neglects the impact of data distribution on the throughput and transfers performance bottlenecks to the network layer. In fact, the overall throughput of permissioned blockchains is co-determined by data production in the consensus layer and data distribution in the network layer. This paper proposes a novel data flow framework composed of Predis and Multi-Zone. The former is a data production strategy for permissioned blockchains that employ leader-based BFT protocols and the latter, its corresponding network topology. Predis enables each consensus node to contribute its idle bandwidth for block content pre-distribution so that a much higher volume of transactions can be confirmed in one consensus round, significantly increasing consensus efficiency. Multi-Zone is a network topology to distribute blocks. It can regulate the bandwidth consumption of consensus nodes at a certain value during data distribution and effectively reduce block propagation latency. To test our framework, we implement Predis based on Hotstuff and PBFT, respectively, and experiments show that Predis significantly improves their throughput by 300% to 800%. Multi-Zone is implemented on BFT-SMaRt and compared with random and star network topologies, and it is shown that Multi-Zone holds excellent scalability and the capability of reducing block propagation latency by at least 50%.

Geo-replication is essential in reliable large-scale cloud applications. We argue that existing replication solutions are too rigid to support today’s diversity of data consistency and performance requirements. Stabilizer is a flexible geo-replication library, supporting user-defined consistency models. The library achieves high performance using control-plane / data-plane separation: control events do not disrupt data flow. Our API offers simple control-plane operators that allow an application to define its desired consistency model: a stability frontier predicate. We build a wide-area K/V store with Stabilizer, a Dropbox-like application, and a prototype pub/sub system to show its versatility and evaluate its performance. When compared with a Paxos-based consistency protocol in an emulated Amazon EC2 wide-area network, experiments show that for a scenario requiring a more accurate consistency model, Stabilizer achieves a 24.75% latency performance improvement. Compared to Apache Pulsar in a real WAN environment, Stabilizer’s dynamic reconfiguration mechanism improves the pub/sub system performance significantly according to our experiment results.

Deep Reinforcement Learning (DRL) achieves great success in various domains. Communication in today's DRL algorithms takes non-negligible time compared to the computation. However, prior DRL frameworks usually focus on computation management while paying little attention to communication optimization, and fail to utilize the opportunity of the communication-computation overlap that hides the communication from the critical path of DRL algorithms. Consequently, communication can take more time than the computation in prior DRL frameworks. In this paper, we present XingTian, a novel DRL framework that co-designs the management of communication and computation in DRL algorithms. XingTian organizes the computation in DRL algorithms in a decentralized way and provides an asynchronous communication channel. XingTian makes the communication execute asynchronously and aggressively and takes advantage of the communication-computation overlapping opportunity from DRL algorithms. Experimental results show that XingTian improves data transmission efficiency and can transmit at least twice as much data per second as the state-of-the-art DRL framework RLLib. DRL algorithms based on XingTian achieve up to 70.71% more throughput than RLLib-based ones with better or similar convergent performance. XingTian maintains high communication efficiency under different scale deployments and the XingTian-based DRL algorithm achieves 91.12% higher throughput than the RLLib-based one when deployed in four machines. XingTian is open-sourced and publicly available at https://github.com/huawei-noah/xingtian.