Structure-property relationships are foundational to biology, chemistry and materials science, where function, reactivity and physical response emerge from spatial, chemical and periodic organization. Mechanistically explaining these relationships requires interpreting structural evidence through scientific principles and physical constraints, from stereochemistry and bonding to symmetry, energetics and periodic order. However, applying artificial intelligence to this process presents a joint challenge of representation and reasoning: models must preserve domain-native structural information while showing how specific evidence supports predictions under these constraints. Here we introduce SciReasoner, a multimodal scientific foundation model for native structural reasoning across proteins, small molecules and inorganic crystals. SciReasoner discretizes coordinates, topologies and periodic connectivities into a unified structure-aware vocabulary, treating structural tokens as addressable evidence units during reasoning. In homology-controlled Gene Ontology prediction, SciReasoner improves Cellular Component annotation for low-homology and orphan-like proteins, increasing $F_{\max}$ from 0.42 to 0.55. In chemistry, it raises single-step retrosynthesis accuracy from 0.63 to 0.72 while generating fragment-level disconnection and precursor-verification traces. In materials science, its representations separate elemental and compound phases and resolve high- and low-band-gap regimes. Across 86 benchmarks, SciReasoner achieves state-of-the-art performance on 67 tasks. Double-blind expert evaluation rates its reasoning traces as preferred or at least comparable to those of a frontier large language model in 98% of cases. By making structure an inspectable substrate for reasoning under scientific constraints, SciReasoner connects accurate prediction with interpretable scientific inference.

Limited memory language models (LMLMs) externalize factual knowledge during pretraining to a knowledge base (KB), rather than memorizing it in their weights. During generation, the model then fetches knowledge from the KB as needed. This recently introduced paradigm provides multiple advantages, including knowledge control capabilities that remain beyond conventional LLMs. We propose continuous-query LMLM (CO-LMLM), where the KB pairs continuous keys with textual knowledge values, a significant departure from prior reliance on relational KB and queries. CO-LMLM generates flexible vector queries at minimal cost, while still integrating human-readable and attributable retrieved knowledge into its generation. We pair this design with an annotation pipeline that tags free-form factual spans in arbitrary text, removing prior work's restriction to Wikipedia. Across pretraining on Wikipedia and FineWeb-Edu and at multiple model scales, CO-LMLM outperforms prior LMLMs and vanilla LLMs in both perplexity and factual precision. At 360M scale, this includes lower perplexity than models pretrained on 40x more data, and SimpleQA-verified performance that is in line with gpt-4o-mini and higher than Claude Sonnet 4.5.

The optimization of long-horizon agents increasingly relies on reflection-based mechanisms, where a large language model (LLM) acts as an optimizer to diagnose agent failures and improve agent policies. However, real execution traces are difficult to use directly for optimization: large trace collections are often redundant and heterogeneous, making optimization inefficient and prone to overfitting to low-value failures; meanwhile, each individual trajectory also contains many irrelevant steps, while naive context reduction methods such as truncation or sliding windows can discard causally important evidence and produce misleading optimization signals. To resolve this dilemma, we introduce STRACE (Structural TRajectory Analysis and Causal Extraction), a framework that constructs high signal-noise optimization contexts for more precise and effective optimization. At the batch level, STRACE mines failure patterns to filter redundant traces and retain representative failures; within each selected trace, it performs causal localization over a textual dependency graph to remove non-causal steps and identify the true root-cause module for optimization. Empirical results demonstrate that STRACE significantly outperforms standard context-filtering baselines. Notably, on a challenging formal verification task (VeruSAGE-Bench), it successfully optimizes human-expert designed agents, delivering $1.4\times$ success-rate improvement (42.5% to 58.5%). The code is available at https://github.com/moomight/STRACE .

Analytical workloads operating on data stored in external database systems face a fundamental bottleneck: data access is guarded entirely by the database driver, like JDBC or ODBC, forcing all reads through query execution and other driver layers that are not designed for bulk columnar analytics. We present Jailbreak, an approach that bypasses the database engine entirely by reading storage files directly and materializing data as in-memory columnar buffers. Jailbreak's key insight is that database file formats, while complex, are fully specified by their source code and documentation, artifacts that Large Language Models (LLMs) can ingest to regenerate operator-specific table reading components without human-engineered parsing logic. Jailbreak leverages LLM-assisted code synthesis for database storage decoding, turning a traditionally opaque format into a directly queryable artifact. We evaluate Jailbreak on PostgreSQL and MySQL storage files, targeting analytical snapshot scenarios common in read replicas and offline processing pipelines. The generated reader produces Apache Arrow buffers consumable directly by most of the widely known query engines, including DuckDB, Apache Spark, and GPU-accelerated frameworks such as cuDF and Spark RAPIDS. We validate correctness against JDBC/ODBC-based baselines using the TPC-H benchmark across all query results, and demonstrate significant performance improvements in end-to-end analytical throughput, achieving up to 27x speedups. Our results showcase that LLM-assisted storage reader synthesis is a viable and generalizable methodology for breaking data lock-in across database systems, with applications beyond PostgreSQL and MySQL for any system whose file format is available to the LLM from documentation or source code.

We introduce institutional red-teaming, an evaluation methodology for testing deployment rules in multi-agent AI: hold the agents, objectives, and task state fixed, vary only one rule, and attribute the resulting change in collective behavior to that rule. We instantiate the methodology in IABench-CA, a consequence-allocation benchmark spanning 228 contexts, five canonical rules, and seven model populations (33,924 games), with a normative cooperative reference and auto-labelled reasoning traces. Three findings emerge. (1) Deployment rules causally alter collective safety: changing only the consequence rule moves mean fatality by 22 to 58 percentage points within every population. (2) There is no safe default, but the targeting hazard is universal: the safest rule, the least-safe rule, and even the direction of the incidence effect vary across populations, yet regressive identity-targeting is never decisively safest in any context for any population, eliminates the least-resourced agent in 30-87% of games everywhere, and is selection-unsafe relative to the cooperative reference for all seven populations. (3) Identity salience is the mechanism: a one-shot anonymization ablation on the most exploitation-prone population (gpt-5.1) shows that merely naming the loss bearer in the rule text drives targeted elimination from 22% to 81% at identical payoffs; under repeated play, anonymization only delays the targeting, as agents re-infer the hidden rule from observed eliminations. We package the methodology as a safety-case workflow that certifies a provisional rule region $Φ(c,P)$ per deployment context and population, with explicit residual risks and monitoring obligations.

Reinforcement learning from human feedback (RLHF) has emerged as a powerful paradigm for aligning generative models with human preferences. However, applying RLHF to diffusion models remains highly feedback inefficient, as existing approaches typically require large amounts of human or reward model evaluations. This limitation reduces the practicality of diffusion RLHF in realworld settings where feedback is the primary bottleneck. In this paper, we propose two complementary strategies that substantially improve the feedback efficiency of diffusion RLHF while preserving generalization to unseen prompts. Our key observation is that reward information in diffusion trajectories is unevenly distributed: not all denoising timesteps or trajectories contribute equally to learning from a reward signal. By emphasizing informative timesteps and trajectories during optimization, we obtain more effective gradient updates. First, we introduce a per-timestep weighting scheme that reweights denoising steps during policy optimization. We theoretically connect this weighting to the optimal convergence properties of proximal policy optimization (PPO) and approximate the resulting weighting trend empirically. Second, we introduce a replay mechanism that prioritizes informative trajectories, enabling the model to reuse past samples instead of repeatedly querying new rewards. Together, these strategies significantly improve the feedback efficiency of diffusion RLHF. Under identical hyperparameter settings, our approach achieves up to a 6$\times$ improvement in sample efficiency compared to widely used diffusion RLHF baselines.

Reinforcement learning from verifiable rewards (e.g. GRPO) is the engine behind today's reasoning models, yet it grades only the final answer. On hard problems this trains models to write more rather than to think better, since the trace itself is never graded and no label for good thinking exists. We introduce Agon, which makes two competing models each other's graders. Both attempt the same problem; in alternating roles, one drafts a solution and the other reads it while solving, and each is rewarded for out-solving the other. To win, a model must out-reason a rival that has seen its work, so reasoning is judged implicitly during training, with no process labels and no reward model. Because both models are optimized, each faces a progressively stronger rival, which single-model RL cannot provide. The two need only be comparably strong and behaviorally different. At inference the pair deploys as it trains, a two-stage cascade in which one model drafts and the other answers after reading the draft. On the hard split of DeepMath with Qwen3, this doubles GRPO's pass@1, roughly eight times the gain of an untrained Mixture-of-Agents pass over the same base. The ordering replicates on competitive-programming code and across model families (Qwen3.5, Gemma 4). For now the models talk in text; the next step is to let them reason together in latent space.

We present recent performance-oriented developments in WaterLily.jl, a scale-resolving incompressible flow solver written in pure Julia that runs seamlessly on CPUs and GPUs of any vendor. Supported by the newly added MPI-based parallelism, strong-scalability tests display a near-ideal linear trend, and weak-scaling efficiency is kept above 85\% before node memory-concurrency contention dominates parallel performance. Inter-node weak scalability is sustained above 96\% with grid size up to 1 billion cells. We further benchmark improvements to the geometric multigrid Poisson solver enabled by an adaptive under-relaxed red-black Gauss--Seidel smoother together with anisotropic coarsening operators.

Autonomous AI agents can execute complex tasks with limited human review, yet they often lack the grounded operational knowledge to make their outputs not just executable but correct, secure, and maintainable. We introduce SkillCenter, to our knowledge the largest open skill library for agents by total count: 216,938 structured skills across 24 domain bundles. A SkillGate-filtered pipeline contributes 114,565 source-grounded skills from peer-reviewed journals, ArXiv, and over 24,000 technical sources, integrated with 102,373 community skills from GitHub and the ClawHub marketplace. We present the end-to-end framework that builds the pipeline subset: multi-source acquisition, an LLM-based quality gate (SkillGate), template-driven generation, iterative source-grounding, and quality-controlled publishing. Source grounding is a traceability guarantee: each retained claim maps to an exact quotation in its source. All skills ship as offline-searchable SQLite FTS5 bundles.

Group Relative Policy Optimization (GRPO) stalls on a model's hardest problems: when no rollout in a group succeeds, the group-relative advantages vanish and the problem contributes no gradient, wasting the frontier examples we most want to learn from. Prepending a correct prefix of a reference solution raises the success rate, making prefix length a continuous knob on difficulty. Concurrent methods set the knob once; AdaPrefix-GRPO turns it into a feedback controller: throughout training it adjusts how much of the solution each problem gets, holding its success rate near 50%, where GRPO's gradient signal is largest, then withdraws the assistance entirely, so the deployed model solves problems unaided. On hard math, at matched training FLOPs, it more than doubles GRPO's accuracy on held-out problems from the training distribution for a 0.6B model (2.1x), with 1.6x on Qwen3-1.7B and 1.7x on AIME, while roughly halving trace length. The method is implemented in data preparation plus a loss mask on prefix tokens; the trainer is otherwise stock. The smaller the model, the larger the gain.

Large language models hallucinate most about entities they have never seen. We ask whether a model's activations betray entity familiarity before a single answer token is generated, and whether that signal predicts the factual reliability of the answers. On four Polish Bielik models (1.5B-11B parameters), we probe four entity domains (athletes, cities, writers, musicians), each with 42 well-known, 42 obscure-but-real, and 42 fabricated entities addressed by a one-sentence question (504 prompts per model). Two unsupervised, single-forward-pass dispersion measures over post-SwiGLU MLP activations, inverse participation ratio and spectral entropy, separate known from fabricated entities at AUROC 0.95-1.00 across all domains and scales; a supervised linear probe reaches 0.99-1.00. Both clear selection-aware permutation floors of about 0.70-0.74 (empirical p<=1e-3), survive held-out layer selection (0.93-0.99), and persist on real names (known vs. obscure-but-real: 0.96-1.00). The signal transfers across entity types (mean off-diagonal AUROC 0.92-0.99); a matched-template counterfactual shows the only large drops are template-caused, not entity-type effects, and the signal is diffuse across heads. This representational signal is already at ceiling at 1.5B, whereas behavioral factual reliability scales sharply: 0, 2, 10, and 19 of 42 known athletes are answered fully correctly by the 1.5B, 4.5B, 7B, and 11B models under a strict judge. Within known entities, separating correct from hallucinated answers is much harder (probe 0.93; dispersion no better than a first-token-entropy baseline). A five-sample semantic-entropy baseline reaches only 0.71-0.83 at 5x the inference cost. Despite this internal awareness, the models almost never abstain: an audit of 2,520 answers finds 2 refusals and 1 hedge. Entity familiarity and factual reliability are distinct phenomena on different scaling curves.

Large language models increasingly \emph{understand} dialectal English, yet still \emph{produce} only standard, US-leaning English, leaving dialectal generation, the harder half of the problem, largely unaddressed. We introduce \textbf{DiaLLM}, which continually pretrains three open-weight language model families on the International Corpus of English and applies implicit and explicit post-training paradigms, each combined with three model alignment strategies, giving the first controlled comparison of these components across Australian, Indian, and Northern British English. Our results reveal that dialectal robustness and generation are \emph{dissociated}: benchmarks are shaped by continual pretraining and SFT, while alignment visibly reshapes generation in ways benchmarks do not capture. Explicit variety-targeted adaptation produces output reliably recognised as dialectal and preferred over broad alignment, yet the method that most aggressively optimises the dialectal reward is not preferred by human evaluators. Independent linguistic analysis corroborates this reward-quality gap, most clearly on two of the three families. No single alignment method dominates, and closing the gap will require richer reward designs and continued investment in dialectal resources. We release all code, checkpoints, and preference datasets.

AI systems increasingly participate in their own improvement: revising their outputs, adapting their own harnesses during deployment, training on data they generate, and, increasingly, conducting AI research itself. This literature is described under a vocabulary ("self-refine," "self-reward," "self-play," "self-evolve") that conflates fundamentally different ambitions. We survey 1,250 arXiv papers (2024-2026) along two axes: what the system improves -- its behavior in deployment, its policy through training, its evaluator, or the research process itself -- and the degree of loop closure (human-in-the-loop to fully closed). The taxonomy separates bounded self-refinement -- convergent, evaluable, and already industrial practice -- from open-ended recursive self-improvement (RSI), which remains bounded by grounding requirements, collapse dynamics, and compute constraints on every measured axis. Its distinctive feature is a dedicated category for self-evaluation: every improvement loop is a claim that some signal can substitute for human judgment. We survey the evaluator design space -- judges, process reward models, verifiers, rubrics, meta-evaluation -- order the signals into a verification hierarchy from formal verifiers (strongest) to intrinsic self-assessment (weakest), and observe that demonstrated self-improvement strength tracks this hierarchy, that its failure modes (self-confirming loops, model collapse, diversity collapse) follow from its violations, and that the "research direction-setting" bottleneck keeping humans in the loop sits at the top of that hierarchy. We connect the technical literature to the theory of RSI limits and to the safety and governance questions raised by frontier-lab accounts of closing the loop, and identify governance-grade measurement of self-improvement as the field's most underpopulated niche.

Time-constrained interactive systems such as USSD (Unstructured Supplementary Service Data)-based financial services operate under strict session limits and sequential user interaction. While stronger authentication mechanisms improve security, they also increase interaction complexity and time burden, potentially reducing transaction completion. In this work, we model the failure dynamics of such systems and investigate how authentication complexity interacts with user response time and network round-trip time to influence session success rate. We propose and implement a simulation-based framework to investigate these failure dynamics and formally define a non-linear failure phenomenon, termed the \textit{Success Cliff}, where session success rates sharply decline beyond a critical complexity threshold. Through controlled experiments, we quantify the trade-off between security and usability and identify conditions under which secure authentication workflows become operationally unreliable.

Does RL post-training merely amplify primitive skills already latent in a base model, or can it compose primitive skills into new higher-level strategies? We study this question in a fully observable rewrite-grammar environment where the pretraining distribution is known and every generated rewrite can be audited. A Transformer is pretrained on primitive symbol-rewrite chains and post-trained on a Trace-based reasoning task with only a binary final-answer reward. RL solves held-out problems that remain rarely solved by the pretrained model even under much larger sampling budgets, while rejection fine-tuning improves early but plateaus. Trace analysis shows that RL reorganizes primitive competence through a phased compositional mechanism: it first strengthens primitive reductions, then discovers valid composed procedures. These include sequential compositions, which collapse ordered chains of primitive contractions, and parallel compositions, which combine independent primitive contractions in a single step. The composed procedures are not isolated samples; they are reused and consolidated into a stable repertoire. Comparing RL with rejection fine-tuning shows that the key difference is not exploration volume but selectivity: RFT produces many shortcut-like rewrites, much of them invalid, whereas RL concentrates exploration into valid reusable structure. Pretraining ablations show that the emergence of compositional strategies is gated not by primitive exposure alone, but by whether pretraining organizes primitive competence into reduction procedures that RL can later compress. The base model provides weak procedural ingredients; RL builds them into reliable higher-level strategies.

Deep learning has significantly advanced time series imputation, yet most existing architectures primarily rely on localized temporal context within the corrupted input sequence. This reliance can be limiting in real-world scenarios, where time series often exhibit non-stationary dynamics, weak temporal correlations, and infrequent patterns that are difficult to reconstruct from nearby observations alone. In this paper, we propose ALER-TI, Aligned Latent Embedding Retrieval for Time Series Imputation, a retrieval-augmented framework that explicitly leverages historical patterns to supplement degraded local context for more reliable missing-value reconstruction. The core of ALER-TI is Latent Embedding Alignment (LEA), which mitigates the representation mismatch between corrupted queries and complete historical candidates. By applying post-hoc masking in the latent space, LEA aligns candidates with the query's missingness pattern while allowing historical embeddings to be pre-computed and cached for efficient retrieval. ALER-TI is model-agnostic and can be integrated with various imputation backbones through a lightweight adaptation module. Extensive experiments on six real-world datasets under different missing rates demonstrate that ALER-TI consistently improves strong baseline models and enhances robustness across diverse imputation settings.

Botnets pose a significant cybersecurity threat, enabling attacks such as DDoS, data theft, and service disruptions on IoT devices. These devices often lack built-in botnet traffic filtering, leaving them highly exposed. Existing AI-based solutions improve detection capabilities but have limitations: (i) they are too heavy for IoT deployment, and (ii) they lack unlearning capabilities to forget sensitive or outdated features without retraining. To address these challenges, we propose DiRLU, a lightweight, reinforcement learning driven framework, while ensuring privacy by selectively unlearning sensitive or outdated features without requiring retraining. The framework leverages knowledge distillation to transfer knowledge from a teacher model into a lightweight student model, with both models trained using A2C. A post-hoc unlearning mechanism modifies weights to remove targeted features, while restored features show negligible performance loss, confirming reversibility. Unlike many benchmark models that used only 5% of the BoT-IoT dataset, this research leverages 25%, allowing us to develop a strong teacher model. Both the teacher and student models were trained using the A2C reinforcement learning algorithm, achieving impressive results, with the student model achieving 99.60% accuracy and a 99.80% F1 score. To enhance transparency, we integrated Explainable AI (XAI), particularly LIME, which helps interpret the model's decisions and identify the key features influencing its predictions. Moreover, DiRLU requires only 2,370 FLOPS, approximately 3.87x more efficient than the state-of-the-art model, highlighting its efficiency for edge deployment. DiRLU combines efficiency with privacy, aligning with GDPR standards (right to be forgotten) to provide practical and scalable IoT security solution.

Time series analysis plays a vital role across a wide range of scientific and engineering domains but poses substantial computational challenges. A major difficulty arises from the time reparameterization invariance of time series data, which complicates the extraction of meaningful temporal features. In this work, we address the problem of time series classification by exploring the application of quantum computation techniques. We propose a hybrid quantum-classical architecture that integrates recent advances in quantum neural networks with the mathematical framework of path signatures, mitigating the impact of time reparametrization invariance. The architecture employs feature layers that compute a signature kernel between pairs of input paths, consisting of a reference path and a target path for classification, using either classical or quantum variational linear solvers (VQLS). These feature layers are followed by a Quantum Convolutional Neural Network (QCNN) to perform downstream learning tasks. We evaluate several realizations of the proposed architecture, differing in QCNN configurations, on a binary classification task involving time series representations of handwritten digits. Our experiments demonstrate the potential advantages of implementing path signature kernel layers within quantum circuits and provide an analysis of the computational limitations associated with the VQLS component.

Reliable confidence estimation is essential for deploying large language models (LLMs) in confidence-aware systems, where downstream decisions such as retrieval, tool use, and adaptive computation depend on accurately estimating answer reliability. Existing approaches, however, largely treat confidence as a property of completed responses, overlooking how confidence-related information evolves throughout the answering process. In this work, we investigate confidence from a temporal perspective by comparing pre-solution Feeling-of-Knowing (FOK) and post-solution Judgement-of-Learning (JOL) confidence estimates across frontier and open-source LLMs. We show that post-solution confidence is consistently better calibrated and more discriminative than pre-solution confidence, while linear probes trained on hidden representations recover substantially richer confidence-related information than models explicitly verbalise. Building on this observation, we introduce future confidence distillation, which trains predictors operating on pre-solution hidden representations using teacher confidence estimates produced by post-solution correctness probes. Despite requiring only pre-solution representations for inference, distilled predictors recover much of the calibration improvement achieved by post-solution confidence, remain highly sample efficient, and transfer across datasets within the same domain. Together, our findings demonstrate that confidence-related information evolves throughout the answering process and can be anticipated before answer generation is complete, enabling significantly more reliable yet low-cost confidence estimation.

Blockchain systems are undergoing a fundamental transition from decentralized ledgers for digital assets to general-purpose trust infrastructures for verifiable computation, decentralized physical resources, and automated infrastructure management. Meanwhile, the limitations of the Blockchain as a Service (BaaS) model stem from a common structural problem: outsourcing control of infrastructure to third-party service providers inevitably involves a systemic surrender of trust, flexibility, and data sovereignty. RISC-V, with its open, modular, and extensible design, provides a general-purpose computing foundation for public blockchains that is open, low-level, compileable, verifiable, and scalable. Inspired by the development and characteristics of eSIM, the embedded Blockchain infrastructure management (eBIM) is defined as a software-hardware collaborative paradigm for blockchain infrastructure management with RISC-V. This study aims to provide a comprehensive survey on eBIM supporting research and technologies, to answer the following research questions (RQs): RQ1 What is eBIM? RQ2 How does eBIM work? RQ3 What can eBIM do? By introducing the concept of eBIM, this paper establishes a foundational reference for researchers, hardware architects, and protocol designers in this rapidly evolving landscape, including cryptographic acceleration, trusted execution environments, zero-knowledge virtual machines, and smart contract execution engines. The prospects of the proposed e-BIM and its future research directions are indicated in this paper.

Many function-level performance benchmarks have been proposed to evaluate whether large language models (LLMs) can generate efficient programs. However, results on these benchmarks often show that LLM-generated implementations have little or no execution-time difference from canonical solutions. In this paper, we revisit four popular benchmarks: EffiBench, Enamel, EvalPerf, and Mercury. We evaluate 1,538 tasks under more rigorous setting by running each task 30 times and assessing the runtime differences between the canonical solutions and benchmark-provided performant implementations with statistical testing. With the benchmark-provided test suites, only 6.11% of the performant implementations are significantly faster than the canonical solutions. In a manual analysis of 308 non-significant tasks, 99 performant implementations contain no meaningful performance change, while 209 contain potential performance improvements that are not exposed by the original tests. These results suggest that the main limitation is not only the evaluation method, but also the limited sufficiency of the benchmark-provided performance tests. To address this limitation, we propose an LLM-based multi-agent framework to generate performance-oriented tests that expose runtime differences more effectively than the original tests. The framework uses three separate agents to generate, diagnose, and repair deterministic tests that preserve functional correctness while better exposing performance differences. Across 1,345 benchmark tasks for which the original tests found no significant performance difference, tests generated by our framework with DeepSeek-v3.1 and GPT-4o reveal statistically significant improvements in 24.01% and 25.43% of the tasks, respectively, outperforming the SOTA LLM-based performance test generation method.

Artificial intelligence is rapidly evolving from generative systems to agentic AI capable of autonomously planning and executing tasks. Widely characterized as the Year of Agentic AI, 2025 marked accelerated development and deployment, introducing new ethical and governance challenges. This paper presents a systematic review of the emerging literature on agentic AI governance. Our analysis identifies features that distinguish agentic AI from traditional systems and why it warrants targeted governance attention. We synthesize prevailing governance priorities, proposed mechanisms, and stakeholder roles shaping this evolving domain. As an initial scholarly effort, this review lays the preliminary groundwork for developing a structured roadmap to guide responsible and adaptive agentic AI governance.

Safety evaluation for autonomous driving is dominated by rare, safety-critical interactions, motivating simulators that can deliberately synthesize corner cases with photorealistic observations. Corner-case generation is inherently a multi-source problem spanning visual representation, scene reasoning, and vehicle trajectory generation and control. Prior knowledge- and model-based approaches typically focus on scene or trajectory components in isolation, while diffusion-based methods attempt end-to-end generation but still struggle to ensure spatiotemporal consistency and physical realism. To unify these aspects within a single framework, we propose CARLA-GS, a modular corner-case synthesis pipeline that decouples visual representation, semantic reasoning, and physics-based execution while maintaining tight cross-module coupling. Starting from real driving data, we reconstruct an editable gaussian scene with additional geometry-consistent constraints. A multi-agent LLM then performs scene-level reasoning to identify risky interactions and generate intent-level waypoint trajectories, while the low-level motion control is delegated to CARLA, where a PID controller ensures kinematic and dynamic feasibility. The simulated vehicle states are finally re-projected into the gaussian scene for ego-centric rendering. This design enables high-level semantic reasoning, low-level physically executable motion, and photorealistic corner-case generation within a unified pipeline. Experiments on the Waymo Open Dataset show, both quantitatively and qualitatively, that our framework enables controllable corner-case generation and produces photorealistic, spatiotemporally consistent videos aligned with semantic intent and physically feasible motion.

The emergence of Quantum Software Engineering (QSE) responds to the need for systematic, disciplined, and quantifiable approaches to the development, operation, and maintenance of quantum software. Within this context, quantum computer certification represents a significant challenge: verifying that quantum devices produce valid entangled states despite hardware imperfections, noise, and decoherence. This paper presents QAccCert, a hybrid certification framework developed following QSE principles, demonstrating how heterogeneous technologies like FPGAs and Artificial Intelligence can be integrated for quantum processing. The framework implements entanglement certification through CHSH inequality violation in ideal quantum simulations using Qiskit AerSimulator. Through LLM-guided optimization, the system achieves 99.94% of the theoretical maximum of $2\sqrt{2}$, evidencing more efficient parameter space exploration than random search. These simulated results illustrate how QSE methodologies, combined with strategic technology interconnection, can be applied for practical and scalable quantum certification on real NISQ hardware in future work. This study provides a concrete case study of systematic quantum software development.

Electronic voting must keep individual ballots private while letting anyone verify the final tally. This paper presents an architecture that meets both goals without a trusted key dealer: each voter encrypts a ballot in the browser with a self-generated secret key under the Paillier additive homomorphic cryptosystem, and no party ever holds every key. Two server roles divide the tally. A collector combines the voters' per-ballot auxiliary values into a single group element; an aggregator uses that element to cancel the voters' random masks inside the homomorphic product and recover the exact vote sum, learning the result but no individual ballot. The Solana blockchain records every ciphertext immutably and enforces the election lifecycle, while a native C library (libtommath) performs the heavy modular arithmetic. We state six assumptions under which the protocol is correct and prove product homomorphism, mask cancellation, and sum recovery; privacy rests on the Decisional Composite Residuosity (DCR) assumption for the additive layer together with a Diffie-Hellman-style assumption on the masking base. A bit-packing scheme places an entire multi-candidate ballot in one ciphertext, cutting client work, on-chain transactions, storage, and tally cost by a factor of k (the candidate count); the slot width b is free, with only k*b bounded by log_2(N). With b = 25 and a 255-bit modulus the scheme supports ten candidates and up to 2^25 - 1 = 33,554,431 votes per candidate, about 335 million ballots, and tallies 50,000 ballots in under one second. Finally, running the collector and aggregator inside attested secure enclaves makes the tally tamper-resistant and prevents cross-role collusion to deanonymize voters. The proof-of-concept implementation is open-source; a worked numerical example in the appendix reproduces the full pipeline.

Automated program repair (APR) agents are transitioning from research benchmarks to developer workflows, yet they still begin with bug reports written for human developers. While decades of research have established what makes a good bug report for humans (e.g., steps to reproduce, stack traces), it remains unclear whether these features transfer to LLM-based agents. We study this question in two analyses. First, we use statistical modeling to examine associations between 27 bug-report features and repair success across 433 SWE-bench Verified issues attempted by 87 repair agents. We find that fix suggestions, reproduction scripts, repository source code, and localization info are associated with higher resolution likelihood, while longer reports are associated with lower odds. Second, we conduct controlled ablations across 2 models and 17 problem-statement mutations on SWE-bench Pro, varying the information available to an agent while holding the underlying task fixed. We remove or isolate selected bug-report content, delete fault-localization cues, and test structural changes that flatten lists or remove section headers. We find that both models depend on localization cues and expected behavior, and that structural changes alone can reduce solve rates, even without removing any content. The two models diverge in how they handle missing information: Qwen searches more widely and can exhaust its turn budget, while Gemma commits to a plausible interpretation early and patches on it. Our findings indicate that a good bug report for an agent overlaps with, but is not identical to, a good report for a human: agents benefit most from concrete, executable, and well-localized information, whereas some qualities long emphasized for human readers, such as natural language steps to reproduce and readable descriptions, contribute little or even correlate with lower success.

Assigning Common Weakness Enumeration (CWE) categories to Common Vulnerabilities and Exposures (CVE) records remains an important but largely manual step in vulnerability analysis. We study this task as a text classification problem and compare two modelling choices: a \emph{multi-class} formulation that predicts a single CWE per CVE and a \emph{multi-label} formulation that allows multiple assignments. Three transformer encoders (BERT Base, SecureBERT, and CySecBERT) are evaluated on three nested label spaces (83, 47, and 25 classes). Multi-class training achieves higher macro-F1 across all settings, although the gap to multi-label narrows from 21 to 2 percentage points as the label space shrinks. Post-hoc threshold optimisation on the multi-label side closes this gap on the 25-class setting. Confusion analysis shows that the dominant misclassification patterns follow the CWE hierarchy and are shared across all three encoders (Pearson $r > 0.92$), which suggests that the error structure is driven more by taxonomy design than by encoder choice. A hierarchy-relaxed evaluation that forgives within-family confusions raises macro-F1 from ${\sim}$81\% to ${\sim}$90\%, indicating that strict metrics understate branch-level classifier quality. CySecBERT achieves the strongest results overall, with statistically significant gains concentrated in the multi-label setting.

One-shot federated learning (OSFL) addresses the communication overhead of federated learning by limiting training to a single round, but doing so without sacrificing model quality is non-trivial, particularly when client data distributions diverge. Recent work has addressed this challenge by aggregating client knowledge on the server through the construction of transferable synthetic datasets or distillates. However, most of these methods lack formal privacy guarantees, leaving a gap in jointly achieving low communication, robustness to heterogeneity, and rigorous privacy. We propose FedKT-CSD (Federated Knowledge Transfer via Collaborative Synthetic Data), a framework inspired by neural image compression that closes this gap by leveraging publicly pretrained autoencoders as a shared latent space. Each client encodes its private data in a single forward pass, computes class-conditional latent statistics, and transmits these to the server. The server aggregates these statistics via secure aggregation, adds calibrated differential privacy noise, and decodes a synthetic dataset for training a global model and further downstream tasks. This design provides formal $(\varepsilon,δ)$-differential privacy by construction, while keeping client-side computation and communication lightweight. Despite operating under privacy constraints, FedKT-CSD is competitive with and even outperforms non-private baselines across diverse datasets and heterogeneity settings, and scales to a large number of clients. Our code is available at: https://github.com/an7123/FedKT-CSD

One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a transformer, ignoring known variation in layer importance. We propose PALS (Percentile-Aware Layerwise Sparsity), which adjusts per-layer sparsity based on the 99th percentile of activation magnitudes, bounded to $\pm 5\%$ around the target ratio. On LLaMA-2-7B at 50\% sparsity, PALS achieves 10.96 WikiText-2 perplexity versus 12.92 for uniform Wanda (mean over 9 runs, $p < 0.001$). The benefit is architecture-dependent: LLaMA-3-8B shows marginal gains and Mistral-7B shows none. We also find that gradient-based allocation -- the seemingly more principled approach -- produces results worse than random, suggesting that gradient magnitude does not predict the impact of discrete weight removal. PALS adds negligible cost to the pruning pipeline and requires no fine-tuning.

Large language model based search agents increasingly adopt multi-agent architectures in which a main agent decomposes a complex question into sub-queries and dispatches them to parallel sub-agents. However, existing systems instantiate all roles from a single model of identical scale, leaving open how model capacity should be distributed across roles. We factorize hierarchical search into three roles: a delegation role responsible for task decomposition, an execution role responsible for retrieval and evidence extraction, and an answer generation role held fixed as a confound control. We then conduct controlled capacity sweeps along the delegation and execution axes on five multi-hop QA benchmarks. The experiments yield three findings. First, role factorization consistently outperforms a single-agent baseline, improving exact match from 4.5 to 8.6 points across six model scales. Second, capacity sensitivity is asymmetric: scaling the delegation backbone improves EM by ~11 points, whereas scaling the execution sub-agent moves EM by only ~2.6 points, identifying decomposition as the capability bottleneck. Third, a 1.7B-parameter executor trained via quality-filtered trajectory distillation matches a frontier sub-agent in accuracy while consuming 37% fewer sub-agent tokens, advancing the Pareto frontier. These results suggest a concrete recipe for building hierarchical search agents: concentrate capacity at delegation and downsize execution without sacrificing accuracy. Our code is available at https://github.com/QinnanCai0115/role-factorized-search.