arXiv:2504.08999v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly augmented with external tools through standardized interfaces like the Model Context Protocol (MCP). However, current MCP implementations face critical limitations: they typically require local process execution through STDIO transports, making them impractical for resource-constrained environments like mobile devices, web browsers, and edge computing. We […]
Governance Architecture for Autonomous Agent Systems: Threats, Framework, and Engineering Practice
arXiv:2603.07191v2 Announce Type: replace-cross Abstract: Autonomous agents powered by large language models introduce a class of execution-layer vulnerabilities — prompt injection, retrieval poisoning, and uncontrolled tool invocation — that existing guardrails fail to address systematically. In this work, we propose the Layered Governance Architecture (LGA), a four-layer framework comprising execution sandboxing (L1), intent verification (L2), […]
Structured Matrix Scaling for Multi-Class Calibration
arXiv:2511.03685v2 Announce Type: replace-cross Abstract: Post-hoc recalibration methods are widely used to ensure that classifiers provide faithful probability estimates. We argue that parametric recalibration functions based on logistic regression can be motivated from a simple theoretical setting for both binary and multiclass classification. This insight motivates the use of more expressive calibration methods beyond standard […]
Physics-Informed Neural Engine Sound Modeling with Differentiable Pulse-Train Synthesis
arXiv:2603.09391v1 Announce Type: cross Abstract: Engine sounds originate from sequential exhaust pressure pulses rather than sustained harmonic oscillations. While neural synthesis methods typically aim to approximate the resulting spectral characteristics, we propose directly modeling the underlying pulse shapes and temporal structure. We present the Pulse-Train-Resonator (PTR) model, a differentiable synthesis architecture that generates engine audio […]
Lightweight Time Series Data Valuation on Time Series Foundation Models via In-Context Finetuning
arXiv:2511.11648v2 Announce Type: replace-cross Abstract: Time series foundation models (TSFMs) have demonstrated increasing capabilities due to their extensive pretraining on large volumes of diverse time series data. Consequently, the quality of time series data is crucial to TSFM performance, rendering an accurate and efficient data valuation of time series for TSFMs indispensable. However, traditional data […]
Property-driven Protein Inverse Folding With Multi-Objective Preference Alignment
arXiv:2603.06748v2 Announce Type: replace-cross Abstract: Protein sequence design must balance designability, defined as the ability to recover a target backbone, with multiple, often competing, developability properties such as solubility, thermostability, and expression. Existing approaches address these properties through post hoc mutation, inference-time biasing, or retraining on property-specific subsets, yet they are target dependent and demand […]
A Causal Graph Approach to Oppositional Narrative Analysis
arXiv:2603.06135v2 Announce Type: replace-cross Abstract: Current methods for textual analysis rely on data annotated within predefined ontologies, often embedding human bias within black-box models. Despite achieving near-perfect performance, these approaches exploit unstructured, linear pattern recognition rather than modeling the structured interactions between entities that naturally emerge in discourse. In this work, we propose a graph-based […]
Dreaming improves memorization in a Hopfield model with bounded synaptic strength
arXiv:2603.09384v1 Announce Type: cross Abstract: The Hopfield model provides a paradigmatic framework for associative memory. Its classical implementation, based on the Hebbian learning rule, suffers from catastrophic forgetting: when one attempts storing too many patterns, the network fails to retrieve any of them. Yet, the Hebbian rule does not take into account that synaptic strength […]
Temporal-Conditioned Normalizing Flows for Multivariate Time Series Anomaly Detection
arXiv:2603.09490v1 Announce Type: cross Abstract: This paper introduces temporal-conditioned normalizing flows (tcNF), a novel framework that addresses anomaly detection in time series data with accurate modeling of temporal dependencies and uncertainty. By conditioning normalizing flows on previous observations, tcNF effectively captures complex temporal dynamics and generates accurate probability distributions of expected behavior. This autoregressive approach […]
OptiRoulette Optimizer: A New Stochastic Meta-Optimizer for up to 5.3x Faster Convergence
arXiv:2603.06613v2 Announce Type: replace-cross Abstract: This paper presents OptiRoulette, a stochastic meta-optimizer that selects update rules during training instead of fixing a single optimizer. The method combines warmup optimizer locking, random sampling from an active optimizer pool, compatibility-aware learning-rate scaling during optimizer transitions, and failure-aware pool replacement. OptiRoulette is implemented as a drop-in, “torch.optim.Optimizer-compatible” component […]
When Learning Rates Go Wrong: Early Structural Signals in PPO Actor-Critic
arXiv:2603.09950v1 Announce Type: cross Abstract: Deep Reinforcement Learning systems are highly sensitive to the learning rate (LR), and selecting stable and performant training runs often requires extensive hyperparameter search. In Proximal Policy Optimization (PPO) actor–critic methods, small LR values lead to slow convergence, whereas large LR values may induce instability or collapse. We analyse this […]
Censored LLMs as a Natural Testbed for Secret Knowledge Elicitation
arXiv:2603.05494v2 Announce Type: replace-cross Abstract: Large language models sometimes produce false or misleading responses. Two approaches to this problem are honesty elicitation — modifying prompts or weights so that the model answers truthfully — and lie detection — classifying whether a given response is false. Prior work evaluates such methods on models specifically trained to […]