Spec-driven development (SDD) with AI coding agents provides a structured workflow, but agents often remain "context blind" in large, evolving repositories, leading to hallucinated APIs and architectural violations. We present Spec Kit Agents, a multi-agent SDD pipeline (with PM and developer roles) that adds phase-level, context-grounding hooks. Read-only probing hooks ground each stage (Specify, Plan, Tasks, Implement) in repository evidence, while validation hooks check intermediate artifacts against the environment. We evaluate 128 runs covering 32 features across five repositories. Context-grounding hooks improve judged quality by +0.15 on a 1-5 composite LLM-as-judge score (+3.0 percent of the full score; Wilcoxon signed-rank, p < 0.05) while maintaining 99.7-100 percent repository-level test compatibility. We further evaluate the framework on SWE-bench Lite, where augmentation hooks improve baseline by 1.7 percent, achieving 58.2 percent Pass@1.

Late-interaction retrieval models rely on hard maximum similarity (MaxSim) to aggregate token-level similarities. Although effective, this winner-take-all pooling rule may structurally bias training dynamics. We provide a mechanistic study of gradient routing and robustness in MaxSim-based retrieval. In a controlled synthetic environment with in-batch contrastive training, we demonstrate that MaxSim induces significantly higher patch-level gradient concentration than smoother alternatives such as Top-k pooling and softmax aggregation. While sparse routing can improve early discrimination, it also increases sensitivity to document length: as the number of document patches grows, MaxSim degrades more sharply than mild smoothing variants. We corroborate these findings on a real-world multi-vector retrieval benchmark, where controlled document-length sweeps reveal similar brittleness under hard max pooling. Together, our results isolate pooling-induced gradient concentration as a structural property of late-interaction retrieval and highlight a sparsity-robustness tradeoff. These findings motivate principled alternatives to hard max pooling in multi-vector retrieval systems.

We consider constrained ergodic resource optimization in wireless networks with graph-structured interference. We train a diffusion model policy to match expert conditional distributions over resource allocations. By leveraging a primal-dual (expert) algorithm, we generate primal iterates that serve as draws from the corresponding expert conditionals for each training network instance. We view the allocations as stochastic graph signals supported on known channel state graphs. We implement the diffusion model architecture as a U-Net hierarchy of graph neural network (GNN) blocks, conditioned on the channel states and additional node states. At inference, the learned generative model amortizes the iterative expert policy by directly sampling allocation vectors from the near-optimal conditional distributions. In a power-control case study, we show that time-sharing the generated power allocations achieves near-optimal ergodic sum-rate utility and near-feasible ergodic minimum-rates, with strong generalization and transferability across network states.

AI-based writing assistants are ubiquitous, yet little is known about how users' mental models shape their use. We examine two types of mental models -- functional or related to what the system does, and structural or related to how the system works -- and how they affect control behavior -- how users request, accept, or edit AI suggestions as they write -- and writing outcomes. We primed participants ($N = 48$) with different system descriptions to induce these mental models before asking them to complete a cover letter writing task using a writing assistant that occasionally offered preconfigured ungrammatical suggestions to test whether the mental models affected participants' critical oversight. We find that while participants in the structural mental model condition demonstrate a better understanding of the system, this can have a backfiring effect: while these participants judged the system as more usable, they also produced letters with more grammatical errors, highlighting a complex relationship between system understanding, trust, and control in contexts that require user oversight of error-prone AI outputs.

The use of LLMs for code generation has naturally extended to code testing and evaluation. As codebases grow in size and complexity, so does the need for automated test generation. Current approaches for LLM-based test generation rely on strategies that maximize immediate coverage gain, a greedy approach that plateaus on code where reaching deep branches requires setup steps that individually yield zero new coverage. Drawing on principles of Bayesian exploration, we treat the program's branch structure as an unknown environment, and an evolving coverage map as a proxy probabilistic posterior representing what the LLM has discovered so far. Our method, CovQValue, feeds the coverage map back to the LLM, generates diverse candidate plans in parallel, and selects the most informative plan by LLM-estimated Q-values, seeking actions that balance immediate branch discovery with future reachability. Our method outperforms greedy selection on TestGenEval Lite, achieving 51-77% higher branch coverage across three popular LLMs and winning on 77-84% of targets. In addition, we build a benchmark for iterative test generation, RepoExploreBench, where they achieve 40-74%. These results show the potential of curiosity-driven planning methods for LLM-based exploration, enabling more effective discovery of program behavior through sequential interaction

In Landmark-Inertial Simultaneous Localisation and Mapping (LI-SLAM), the positions of landmarks in the environment and the robot's pose relative to these landmarks are estimated using landmark position measurements, and measurements from the Inertial Measurement Unit (IMU). However, the robot and landmark positions in the inertial frame, and the yaw of the robot, are not observable in LI-SLAM. This paper proposes a nonlinear observer for LI-SLAM that overcomes the observability constraints with the addition of intermittent GNSS position and magnetometer measurements. The full-state error dynamics of the proposed observer is shown to be both almost-globally asymptotically stable and locally exponentially stable, and this is validated using simulations.

We study compiled AI, a paradigm in which large language models generate executable code artifacts during a compilation phase, after which workflows execute deterministically without further model invocation. This paradigm has antecedents in prior work on declarative pipeline optimization (DSPy) and hybrid neural-symbolic planning (LLM+P); our contribution is a systems-oriented study of its application to high-stakes enterprise workflows, with particular emphasis on healthcare settings where reliability and auditability are critical. By constraining generation to narrow business-logic functions embedded in validated templates, compiled AI trades runtime flexibility for predictability, auditability, cost efficiency, and reduced security exposure. We introduce (i) a system architecture for constrained LLM-based code generation, (ii) a four-stage generation-and-validation pipeline that converts probabilistic model output into production-ready code artifacts, and (iii) an evaluation framework measuring operational metrics including token amortization, determinism, reliability, security, and cost. We evaluate on two task types: function-calling (BFCL, n=400) and document intelligence (DocILE, n=5,680 invoices). On function-calling, compiled AI achieves 96% task completion with zero execution tokens, breaking even with runtime inference at approximately 17 transactions and reducing token consumption by 57x at 1,000 transactions. On document intelligence, our Code Factory variant matches Direct LLM on key field extraction (KILE: 80.0%) while achieving the highest line item recognition accuracy (LIR: 80.4%). Security evaluation across 135 test cases demonstrates 96.7% accuracy on prompt injection detection and 87.5% on static code safety analysis with zero false positives.

Large language models (LLMs) often generate code that is functionally correct but inefficient in runtime and memory. Prior approaches to improving code efficiency typically rely on absolute execution feedback, such as profiling a single program's runtime or memory usage, which is costly and provides weak guidance for refinement. We propose Relative Contrastive Feedback (RCF), an inference-time feedback mechanism that requires no model fine-tuning or parameter updates. RCF compares two structurally similar programs for the same task and highlights the differences associated with better efficiency. Building on this idea, we introduce EffiPair, an inference-time iterative refinement framework that operates entirely at test time by generating multiple candidate solutions, identifying informative program pairs with large efficiency gaps, summarizing their execution differences into lightweight feedback, and using this signal to produce more efficient solutions. By replacing isolated scalar feedback with pairwise contrastive comparisons, EffiPair provides more direct guidance while reducing profiling and prompting overhead. Experiments on code-efficiency benchmarks show that EffiPair consistently improves efficiency while preserving correctness. For instance, with DeepSeek-Chat V3.2, EffiPair achieves up to 1.5x speedup over generation without performance feedback, while reducing token usage by more than 90% compared to prior work.

Prior authorization (PA) requires interpretation of complex and fragmented coverage policies, yet existing retrieval-augmented systems rely on static top-$K$ strategies with fixed numbers of retrieved sections. Such fixed retrieval can be inefficient and gather irrelevant or insufficient information. We model policy retrieval for PA as a sequential decision-making problem, formulating adaptive retrieval as a Markov Decision Process (MDP). In our system, an agent iteratively selects policy chunks from a top-$K$ candidate set or chooses to stop and issue a decision. The reward balances decision correctness against retrieval cost, capturing the trade-off between accuracy and efficiency. We train policies using Conservative Q-Learning (CQL), Implicit Q-Learning (IQL), and Direct Preference Optimization (DPO) in an offline RL setting on logged trajectories generated from baseline retrieval strategies over synthetic PA requests derived from publicly available CMS coverage data. On a corpus of 186 policy chunks spanning 10 CMS procedures, CQL achieves 92% decision accuracy (+30 percentage points over the best fixed-$K$ baseline) via exhaustive retrieval, while IQL matches the best baseline accuracy using 44% fewer retrieval steps and achieves the only positive episodic return among all policies. Transition-level DPO matches CQL's 92% accuracy while using 47% fewer retrieval steps (10.6 vs. 20.0), occupying a "selective-accurate" region on the Pareto frontier that dominates both CQL and BC. A behavioral cloning baseline matches CQL, confirming that advantage-weighted or preference-based policy extraction is needed to learn selective retrieval. Lambda ablation over step costs $λ\in \{0.05, 0.1, 0.2\}$ reveals a clear accuracy-efficiency inflection: only at $λ= 0.2$ does CQL transition from exhaustive to selective retrieval.

Enterprise multi-agent AI systems produce thousands of inter-agent interactions per hour, yet existing observability tools capture these dependencies without enforcing anything. OpenTelemetry and Langfuse collect telemetry but treat governance as a downstream analytics concern, not a real-time enforcement target. The result is an "observe-but-do-not-act" gap where policy violations are detected only after damage is done. We present Governance-Aware Agent Telemetry (GAAT), a reference architecture that closes the loop between telemetry collection and automated policy enforcement for multi-agent systems. GAAT introduces (1) a Governance Telemetry Schema (GTS) extending OpenTelemetry with governance attributes; (2) a real-time policy violation detection engine using OPA-compatible declarative rules under sub-200 ms latency; (3) a Governance Enforcement Bus (GEB) with graduated interventions; and (4) a Trusted Telemetry Plane with cryptographic provenance.

Artificial intelligence applications in autonomous driving, medical diagnostics, and financial systems increasingly demand machine learning models that can provide robust uncertainty quantification, interpretability, and noise resilience. Bayesian decision trees (BDTs) are attractive for these tasks because they combine probabilistic reasoning, interpretable decision-making, and robustness to noise. However, existing hardware implementations of BDTs based on CPUs and GPUs are limited by memory bottlenecks and irregular processing patterns, while multi-platform solutions exploiting analog content-addressable memory (ACAM) and Gaussian random number generators (GRNGs) introduce integration complexity and energy overheads. Here we report a monolithic FDSOI-FeFET hardware platform that natively supports both ACAM and GRNG functionalities. The ferroelectric polarization of FeFETs enables compact, energy-efficient multi-bit storage for ACAM, and band-to-band tunneling in the gate-to-drain overlap region and subsequent hole storage in the floating body provides a high-quality entropy source for GRNG. System-level evaluations demonstrate that the proposed architecture provides robust uncertainty estimation, interpretability, and noise tolerance with high energy efficiency. Under both dataset noise and device variations, it achieves over 40% higher classification accuracy on MNIST compared to conventional decision trees. Moreover, it delivers more than two orders of magnitude speedup over CPU and GPU baselines and over four orders of magnitude improvement in energy efficiency, making it a scalable solution for deploying BDTs in resource-constrained and safety-critical environments.

Generative recommendation (GeneRec) has introduced a new paradigm that represents items as discrete semantic tokens and predicts items in a generative manner. Despite its strong performance across multiple recommendation tasks, existing GeneRec approaches still suffer from severe popularity bias and may even exacerbate it. In this work, we conduct a comprehensive empirical analysis to uncover the root causes of this phenomenon, yielding two core insights: 1) imbalanced tokenization inherits and can further amplify popularity bias from historical item interactions; 2) current training procedures disproportionately favor popular tokens while neglecting semantic relationships among tokens, thereby intensifying popularity bias. Building on these insights, we propose CRAB, a post-hoc debiasing strategy for GeneRec that alleviates popularity bias by mitigating frequency imbalance among semantic tokens. Specifically, given a well-trained model, we first rebalance the codebook by splitting over-popular tokens while preserving their hierarchical semantic structure. Based on the adjusted codebook, we further introduce a tree-structured regularizer to enhance semantic consistency, encouraging more informative representations for unpopular tokens during training. Experiments on real-world datasets demonstrate that CRAB significantly improves recommendation performance by effectively alleviating popularity bias.

For hybrid systems exhibiting periodic behavior, analyzing the invariant set containing the limit cycle is a natural way to study the robustness of the closed-loop system. However, computing these sets can be computationally expensive, especially when applied to contact-rich cyber-physical systems such as legged robots. In this work, we extend existing methods for overapproximating reachable sets of continuous systems using parametric embeddings to compute a forward-invariant set around the nominal trajectory of a simplified model of a bipedal robot. Our three-step approach (i) computes an overapproximating reachable set around the nominal continuous flow, (ii) catalogs intersections with the guard surface, and (iii) passes these intersections through the reset map. If the overapproximated reachable set after one step is a strict subset of the initial set, we formally verify a forward invariant set for this hybrid periodic orbit. We verify this condition on the bipedal walker model numerically using immrax, a JAX-based library for parametric reachable set computation, and use it within a bi-level optimization framework to design a tracking controller that maximizes the size of the invariant set.

Poincare return maps are a fundamental tool for analyzing periodic orbits in hybrid dynamical systems, including legged locomotion, power electronics, and other cyber-physical systems with switching behavior. The Poincare return map captures the evolution of the hybrid system on a guard surface, reducing the stability analysis of a periodic orbit to that of a discrete-time system. While linearization provides local stability information, assessing robustness to disturbances requires identifying invariant sets of the state space under the return dynamics. However, computing such invariant sets is computationally difficult, especially when system dynamics are only available through forward simulation. In this work, we propose an algorithmic framework leveraging sampling-based optimization to compute a finite-step invariant ellipsoid around a nominal periodic orbit using sampled evaluations of the return map. The resulting solution is accompanied by probabilistic guarantees on finite-step invariance satisfying a user-defined accuracy threshold. We demonstrate the approach on two low-dimensional systems and a compass-gait walking model.

Instructed code editing, where an LLM modifies existing code based on a natural language instruction, accounts for roughly 19% of real-world coding assistant interactions. Yet very few benchmarks directly evaluate this capability. From a survey of over 150 code-related benchmarks, we find that only two, CanItEdit and EDIT-Bench, target instructed code editing with human-authored instructions and test-based evaluation. We audit both by comparing their programming languages, edit intents, and application domains against distributions observed in the wild (Copilot Arena, AIDev, GitHub Octoverse), and by measuring test counts, statement coverage, and test scope across all 213 problems. Both benchmarks concentrate over 90\% of evaluation on Python while TypeScript, GitHub's most-used language, is absent. Backend and frontend development, which together constitute 46% of real-world editing activity, are largely missing, and documentation, testing, and maintenance edits (31.4% of human PRs) have zero representation. Both benchmarks have modest test counts (CanItEdit median 13, EDIT-Bench median 4), though CanItEdit compensates with near-complete whole-file coverage and fail-before/pass-after validation. 59\% of EDIT-Bench's low-coverage suites would not detect modifications outside the edit region. EDIT-Bench has 15 problems that are not solved by any of 40 LLMs and 11 of these problems trace failures to poor benchmark artifacts rather than model limitations. Further, 29% of EDIT-Bench problems and 6% of CanItEdit problems share a codebase with at least one other problem within the benchmark. In summary, these benchmarks measure a narrower construct than deployment decisions require. We therefore propose six empirically grounded desiderata and release all audit artifacts so the community can build instructed code-editing benchmarks whose scores reliably reflect real-world editing capability.

We propose ScalarFedLQR, a communication-efficient federated algorithm for model-free learning of a common policy in linear quadratic regulator (LQR) control of heterogeneous agents. The method builds on a decomposed projected gradient mechanism, in which each agent communicates only a scalar projection of a local zeroth-order gradient estimate. The server aggregates these scalar messages to reconstruct a global descent direction, reducing per-agent uplink communication from O(d) to O(1), independent of the policy dimension. Crucially, the projection-induced approximation error diminishes as the number of participating agents increases, yielding a favorable scaling law: larger fleets enable more accurate gradient recovery, admit larger stepsizes, and achieve faster linear convergence despite high dimensionality. Under standard regularity conditions, all iterates remain stabilizing and the average LQR cost decreases linearly fast. Numerical results demonstrate performance comparable to full-gradient federated LQR with substantially reduced communication.

We present Nidus, a governance runtime that mechanizes the V-model for AI-assisted software delivery. In the self-hosting deployment, three LLM families (Claude, Gemini, Codex) delivered a 100,000-line system under proof obligations verified against the current obligation set on every commit. The system governed its own construction. Engineering invariants - traced requirements, justified architecture, evidenced deliveries - cannot be reliably maintained as learned behavior; assurance requires enforcement by a mechanism external to the proposer. Nidus externalizes the engineering methodology into a decidable artifact verified on every mutation before persistence. Organizational standards compile into guidebooks - constraint libraries imported by governed projects and enforced by decidable evaluation. Four contributions: (1) recursive self-governance - the constraint surface constrains mutations to itself; (2) stigmergic coordination - friction from the surface routes agents without central control; (3) proximal spec reinforcement - the living artifact externalizes the engineering context that RL and long-chain reasoning try to internalize; the specification is the reward function, UNSAT verdicts shape behavior at inference time, no weight updates; (4) governance theater prevention - compliance evidence cannot be fabricated within the modeled mutation path. The constraint surface compounds: each obligation permanently eliminates a class of unengineered output. The artifact's development history is a formal development - every state satisfies all active obligations, and the obligation set grows monotonically.

Music-grounded mashup video creation is a challenging form of video non-linear editing, where a system must compose a coherent timeline from large collections of source videos while aligning with music rhythm, user intent, story completeness, and long-range structural constraints. Existing approaches typically rely on fixed pipelines or simplified retrieval-and-concatenation paradigms, limiting their ability to adapt to diverse prompts and heterogeneous source materials. In this paper, we present GLANCE, a global-local coordination multi-agent framework for music-grounded nonlinear video editing. GLANCE adopts a bi-loop architecture for better editing practice: an outer loop performs long-horizon planning and task-graph construction, and an inner loop adopts the "Observe-Think-Act-Verify" flow for segment-wise editing tasks and their refinements. To address the cross-segment and global conflict emerging after subtimelines composition, we introduce a dedicated global-local coordination mechanism with both preventive and corrective components, which includes a novelly designed context controller, conflict region decomposition module, and a bottom-up dynamic negotiation mechanism. To support rigorous evaluation, we construct MVEBench, a new benchmark that factorizes editing difficulty along task type, prompt specificity, and music length, and propose an agent-as-a-judge evaluation framework for scalable multi-dimensional assessment. Experimental results show that GLANCE consistently outperforms prior research baselines and open-source product baselines under the same backbone models. With GPT-4o-mini as the backbone, GLANCE improves over the strongest baseline by 33.2% and 15.6% on two task settings, respectively. Human evaluation further confirms the quality of the generated videos and validates the effectiveness of the proposed evaluation framework.

Data movement is the primary bottleneck in modern computing systems. For loop-based programs common in high-performance computing (HPC) and AI workloads, including matrix multiplication, tensor contraction, stencil computation, and einsum operations, the cost of moving data through the memory hierarchy often exceeds the cost of arithmetic. This paper presents AutoLALA, an open-source tool that analyzes data locality in affine loop programs. The tool accepts programs written in a small domain-specific language (DSL), lowers them to polyhedral sets and maps, and produces closed-form symbolic formulas for reuse distance and data movement complexity. AutoLALA implements the fully symbolic locality analysis of Zhu et al. together with the data movement distance (DMD) framework of Smith et al. In particular, it computes reuse distance as the image of the access space under the access map, avoiding both stack simulation and Denning's recursive working-set formulation. We describe the DSL syntax and its formal semantics, the polyhedral lowering pipeline that constructs timestamp spaces and access maps via affine transformations, and the sequence of Barvinok counting operations used to derive symbolic reuse-interval and reuse-distance distributions. The system is implemented in Rust as a modular library spanning three crates, with safe bindings to the Barvinok library. We provide both a command-line interface and an interactive web playground with LaTeX rendering of the output formulas. The tool handles arbitrary affine loop nests, covering workloads such as tensor contractions, einsum expressions, stencil computations, and general polyhedral programs.

Integration-by-parts (IBP) reduction of Feynman integrals to master integrals is a key computational bottleneck in precision calculations in high-energy physics. Traditional approaches based on the Laporta algorithm require solving large systems of equations, leading to memory consumption that grows rapidly with integral complexity. We present SAILIR (Self-supervised AI for Loop Integral Reduction), a new machine learning approach in which a transformer-based classifier guides the reduction of integrals one step at a time in a fully online fashion. The classifier is trained in an entirely self-supervised manner on synthetic data generated by a scramble/unscramble procedure: known reduction identities are applied in reverse to build expressions of increasing complexity, and the classifier learns to undo these steps. When combined with beam search and a highly parallelized, asynchronous, single-episode reduction strategy, SAILIR can reduce integrals of arbitrarily high weight with bounded memory. We benchmark SAILIR on the two-loop triangle-box topology, comparing against the state-of-the-art IBP reduction code Kira across 16 integrals of varying complexity. While SAILIR is slower in wall-clock time, its per-worker memory consumption remains approximately flat regardless of integral complexity, in contrast to Kira whose memory grows rapidly with complexity. For the most complex integrals considered here, SAILIR uses only 40\% of the memory of Kira while achieving comparable reduction times. This demonstrates a fundamentally new paradigm for IBP reduction in which the memory bottleneck of Laporta-based approaches could be entirely overcome, potentially opening the door to precision calculations that are currently intractable.

Efficient inference with Large Language Models (LLMs) increasingly relies on Key-Value (KV) caches to store previously computed key and value vectors at each layer. These caches are essential to minimize redundant computation during autoregressive token generation, lowering computational complexity from quadratic to linear. However, the growth of KV caches has posed significant system-level challenges, particularly as model sizes increase, context lengths grow, and concurrent requests compete for limited memory resources. Even though several recent frameworks for KV cache management have emerged, their comparative trade-offs in memory consumption and inference performance have not been fully understood, especially under varying request sizes and model configurations. In this work, we conduct an empirical study of three state-of-the-art KV cache management frameworks: vLLM, InfiniGen, and H2O. These frameworks employ techniques such as tensor offloading, token eviction heuristics, and speculative scheduling to balance memory usage and performance. We evaluate their performance in terms of a range of metrics such as latency, throughput, and memory usage across a spectrum of key parameters including request rates, model sizes, and sparsity levels. Our results pinpoint the conditions for each framework to perform the best, revealing the most suitable selection and configuration of KV cache strategies under memory and performance constraints.

This paper introduces a novel generative framework for synthesising forward-looking, càdlàg stochastic trajectories that are sequentially consistent with time-evolving path-law proxies, thereby incorporating anticipated structural breaks, regime shifts, and non-autonomous dynamics. By framing path synthesis as a sequential matching problem on restricted Skorokhod manifolds, we develop the \textit{Anticipatory Neural Jump-Diffusion} (ANJD) flow, a generative mechanism that effectively inverts the time-extended Marcus-sense signature. Central to this approach is the Anticipatory Variance-Normalised Signature Geometry (AVNSG), a time-evolving precision operator that performs dynamic spectral whitening on the signature manifold to ensure contractivity during volatile regime shifts and discrete aleatoric shocks. We provide a rigorous theoretical analysis demonstrating that the joint generative flow constitutes an infinitesimal steepest descent direction for the Maximum Mean Discrepancy functional relative to a moving target proxy. Furthermore, we establish statistical generalisation bounds within the restricted path-space and analyse the Rademacher complexity of the whitened signature functionals to characterise the expressive power of the model under heavy-tailed innovations. The framework is implemented via a scalable numerical scheme involving Nyström-compressed score-matching and an anticipatory hybrid Euler-Maruyama-Marcus integration scheme. Our results demonstrate that the proposed method captures the non-commutative moments and high-order stochastic texture of complex, discontinuous path-laws with high computational efficiency.

This paper presents a closed-loop system for software lifecycle management framed as a control architecture rather than a code-generation tool. The system manages a backlog of approximately 1,602 rows across seven task families, ingests 13 structured source documents, and executes a deterministic seven-stage pipeline implemented as seven scheduled automation lanes. The automation stack comprises approximately 12,661 lines of Python across 23 scripts plus 6,907 lines of versioned prompt specifications, with checkpoint-based time budgets, 101 exception handlers, and 12 centralized lock mechanisms implemented through four core functions and eight reusable patterns. A Jira Status Contract provides externally observable collision locking, and a degraded-mode protocol supports continued local operation when Jira is unavailable. Artificial-intelligence assistance is bounded by structured context packages, configured resource caps, output re-validation, and human review gates. A formal evaluation of the initial 152-run window yielded 100% terminal-state success with a 95% Clopper-Pearson interval of [97.6%, 100%]; the system has since accumulated more than 795 run artifacts in continuous operation. Three rounds of adversarial code review identified 51 findings, all closed within the study scope (48 fully remediated, 3 closed with deferred hardening), with zero false negatives within the injected set. In an autonomous security ticket family of 10 items, six were completed through pipeline-autonomous dispatch and verification, two required manual remediation, and two were closed by policy decision. The results indicate that bounded, traceable lifecycle automation is practical when autonomy is embedded within explicit control, recovery, and audit mechanisms.

This work presents a comparative analysis of embedding-based and generative models for classifying geoscience technical documents. Using a multi-disciplinary benchmark dataset, we evaluated the trade-offs between model accuracy, stability, and computational cost. We find that generative Vision-Language Models (VLMs) like Qwen2.5-VL, enhanced with Chain-of-Thought (CoT) prompting, achieve superior zero-shot accuracy (82%) compared to state-of-the-art multimodal embedding models like QQMM (63%). We also demonstrate that while supervised fine-tuning (SFT) can improve VLM performance, it is sensitive to training data imbalance.

We introduce the Hiremath Early Detection (HED) Score, a principled, measure-theoretic evaluation criterion for quantifying the time-value of information in systems operating over non-stationary stochastic processes subject to abrupt regime transitions. Existing evaluation paradigms, chiefly the ROC/AUC framework and its downstream variants, are temporally agnostic: they assign identical credit to a detection at t + 1 and a detection at t + tau for arbitrarily large tau. This indifference to latency is a fundamental inadequacy in time-critical domains including cyber-physical security, algorithmic surveillance, and epidemiological monitoring. The HED Score resolves this by integrating a baseline-neutral, exponentially decaying kernel over the posterior probability stream of a target regime, beginning precisely at the onset of the regime shift. The resulting scalar simultaneously encodes detection acuity, temporal lead, and pre-transition calibration quality. We prove that the HED Score satisfies three axiomatic requirements: (A1) Temporal Monotonicity, (A2) Invariance to Pre-Attack Bias, and (A3) Sensitivity Decomposability. We further demonstrate that the HED Score admits a natural parametric family indexed by the Hiremath Decay Constant (lambda_H), whose domain-specific calibration constitutes the Hiremath Standard Table. As an empirical vehicle, we present PARD-SSM (Probabilistic Anomaly and Regime Detection via Switching State-Space Models), which couples fractional Stochastic Differential Equations (fSDEs) with a Switching Linear Dynamical System (S-LDS) inference backend. On the NSL-KDD benchmark, PARD-SSM achieves a HED Score of 0.0643, representing a 388.8 percent improvement over a Random Forest baseline (0.0132), with statistical significance confirmed via block-bootstrap resampling (p < 0.001). We propose the HED Score as the successor evaluation standard to ROC/AUC.

Safety-aligned LLMs go through refusal training to reject harmful requests, but whether these mechanisms remain effective under emotionally charged stimuli is unexplored. We introduce FreakOut-LLM, a framework investigating whether emotional context compromises safety alignment in adversarial settings. Using validated psychological stimuli, we evaluate how emotional priming through system prompts affects jailbreak susceptibility across ten LLMs. We test three conditions (stress, relaxation, neutral) using scenarios from established psychological protocols, plus a no-prompt baseline, and evaluate attack success using HarmBench on AdvBench prompts. Stress priming increases jailbreak success by 65.2\% compared to neutral conditions (z = 5.93, p < 0.001; OR = 1.67, Cohen's d = 0.28), while relaxation priming produces no effect (p = 0.84). Five of ten models show significant vulnerability, with the largest effects concentrated in open-weight models. Logistic regression on 59,800 queries confirms stress as the sole significant condition predictor after controlling for prompt length (p = 0.61) and model identity. Measured psychological state strongly predicts attack success (|r|\geq0.70 across five instruments; all p < 0.001 in individual-level logistic regression). These results establish emotional context as a measurable attack surface with implications for real-world AI deployment in high-stress domains.

AI coding agents select frameworks, scaffold infrastructure, and wire integrations, often in seconds. These are architectural decisions, yet almost no one reviews them as such. We identify five mechanisms by which agents make implicit architectural choices and propose six prompt-architecture coupling patterns that map natural-language prompt features to the infrastructure they require. The patterns range from contingent couplings (structured output validation) that may weaken as models improve to fundamental ones (tool-call orchestration) that persist regardless of model capability. An illustrative demonstration confirms that prompt wording alone produces structurally different systems for the same task. We term the phenomenon vibe architecting, architecture shaped by prompts rather than deliberate design, and outline review practices, decision records, and tooling to bring these hidden decisions under governance.

Recent advances in large language models (LLMs) have opened new opportunities for recommender systems by enabling rich semantic understanding and reasoning about user interests and item attributes. However, as privacy regulations tighten, incorporating user data into LLM-based recommendation (LLMRec) introduces significant privacy risks, making unlearning algorithms increasingly crucial for practical deployment. Despite growing interest in LLMRec unlearning, most existing approaches formulate unlearning as a weighted combination of forgetting and retaining objectives while updating model parameters in a uniform manner. Such formulations inevitably induce gradient conflicts between the two objectives, leading to unstable optimization and resulting in either ineffective unlearning or severe degradation of model utility. Moreover, the unlearning procedure remains largely black-box, undermining its transparency and trustworthiness. To tackle these challenges, we propose CURE, a circuit-aware unlearning framework that disentangles model components into functionally distinct subsets and selectively updates them. Here, a circuit refers to a computational subgraph that is causally responsible for task-specific behaviors. Specifically, we extract the core circuits underlying item recommendation and analyze how individual modules within these circuits contribute to the forget and retain objectives. Based on this analysis, these modules are categorized into forget-specific, retain-specific, and task-shared groups, each subject to function-specific update rules to mitigate gradient conflicts during unlearning. Experiments on real-world datasets show that our approach achieves more effective unlearning than existing baselines.

Coding agents repeatedly consume long tool observations even though only a small fraction of each observation matters for the next step. We study task-conditioned tool-output pruning: given a focused query and one tool output, return the smallest verbatim evidence block the agent should inspect next. We introduce a benchmark of 11,477 examples built from SWE-bench repository interactions and synthetic multi-ecosystem tool outputs, with a manually curated 618-example test set. We fine-tune Qwen 3.5 2B with LoRA and compare it against larger zero-shot models and heuristic pruning baselines. Our model reaches 0.86 recall and 0.80 F1 while removing 92% of input tokens, outperforming zero-shot Qwen 3.5 35B A3B by 11 recall points and all heuristic baselines by a wide margin.

Software supply chain security compromises often stem from cascaded interactions of vulnerabilities, for example, between multiple vulnerable components. Yet, Software Bill of Materials (SBOM)-based pipelines for security analysis typically treat scanner findings as independent per-CVE (Common Vulnerabilities and Exposures) records. We propose a new research direction based on learning multi-vulnerability attack chains through a novel SBOM-driven graph-learning approach. This treats SBOM structure and scanner outputs as a dependency-constrained evidence graph rather than a flat list of vulnerabilities. We represent vulnerability-enriched CycloneDX SBOMs as heterogeneous graphs whose nodes capture software components and known vulnerabilities (i.e, CVEs), connected by typed relations, such as dependency and vulnerability links. We train a Heterogeneous Graph Attention Network (HGAT) to predict whether a component is associated with at least one known vulnerability as a feasibility check for learning over this structure. Additionally, we frame the discovery of cascading vulnerabilities as CVE-pair link prediction using a lightweight Multi-Layer Perceptron (MLP) neural network trained on documented multi-vulnerability chains. Validated on 200 real-world SBOMs from the Wild SBOMs public dataset, the HGAT component classifier achieves 91.03% Accuracy and 74.02% F1-score, while the cascade predictor model (MLP) achieves a Receiver Operating Characteristic - Area Under Curve (ROC-AUC) of 0.93 on a seed set of 35 documented attack chains.