arXiv:2605.01794v1 Announce Type: cross Abstract: Efficient radar resource allocation is a fundamental yet computationally challenging problem, as optimal solutions typically require iterative optimization with high complexity. Motivated by the need for real-time scheduling, robust generalization, and low data dependency, this paper proposes a novel paradigm that leverages large language model (LLM)-guided evolutionary search (AlphaEvolve) to […]
Logistic Gene Regulatory Networks: Prevention of Expression Shutdown, and Numerical Stability Beyond Hill Function
arXiv:2605.01056v1 Announce Type: new Abstract: Hill functions, the standard tool for modelling gene regulatory networks, carry three structural flaws when the cooperativity exponent is non-integer: loss of global smoothness, silent complex-valued arithmetic corruption of ODE trajectories, and an identically zero basal production rate that traps bistable models in off-states. Logistic functions $f^pm$, being globally $C^infty$, […]
On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization
arXiv:2605.02141v1 Announce Type: cross Abstract: Kullback-Leibler (KL) regularization is widely used in offline decision-making and offers several benefits, motivating recent work on the sample complexity of offline learning with respect to KL-regularized performance metrics. Nevertheless, the exact sample complexity of KL-regularized offline learning remains largely from fully characterized. In this paper, we study this question […]
Modelling the electrophysiological interactions between human pluripotent cell-derived cardiomyocite grafts and host ventricular tissue
arXiv:2605.01083v1 Announce Type: new Abstract: Human pluripotent stem cell-derived cardiomyocytes (hPSC-CMs) are a promising therapy for regenerating myocardium after infarction, but their use is limited by graft-related arrhythmias that frequently occur shortly after transplantation. Experimental studies indicate that these arrhythmias can originate within the graft, which may act as an ectopic pacemaker, yet the mechanisms […]
Beyond Static Sandboxing: Learned Capability Governance for Autonomous AI Agents
arXiv:2604.11839v2 Announce Type: replace-cross Abstract: Autonomous AI agents built on open-source runtimes such as OpenClaw expose every available tool to every session by default, regardless of the task. A summarization task receives the same shell execution, subagent spawning, and credential access capabilities as a code deployment task, a 15x overprovision ratio that we call the […]
Counterfactual Reasoning in Automated Planning
arXiv:2605.02603v1 Announce Type: new Abstract: Automated planning traditionally assumes that all aspects of a planning task (initial state, goals, and available actions) are fully specified in advance, an approach well-suited to domains with fixed rules and deterministic execution. However, real-world planning often requires flexibility, allowing for deviations from the original task parameters in response to […]
HeavySkill: Heavy Thinking as the Inner Skill in Agentic Harness
arXiv:2605.02396v1 Announce Type: new Abstract: Recent advances in agentic harness with orchestration frameworks that coordinate multiple agents with memory, skills, and tool use have achieved remarkable success in complex reasoning tasks. However, the underlying mechanism that truly drives performance remains obscured behind intricate system designs. In this paper, we propose HeavySkill, a perspective that views […]
Submodular Benchmark Selection
arXiv:2605.02209v1 Announce Type: new Abstract: Evaluating large language models across many benchmarks is expensive, yet many benchmarks are highly correlated. We formalize the selection of a small, informative subset as submodular maximization under a multivariate Gaussian model. Entropy (log-determinant covariance) and mutual information between selected and remaining benchmarks arise as natural objectives. Both are submodular; […]
Complexity Horizons of Compressed Models in Analog Circuit Analysis
arXiv:2605.02285v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) for specialized engineering domains, such as circuit analysis, often faces a trade-off between reasoning accuracy and computational efficiency. Traditional evaluation methods treat model performance as a flat metric, failing to account for the hierarchical nature of engineering knowledge. We propose a performance-aware model […]
Standing on the Shoulders of Giants: Stabilized Knowledge Distillation for Cross–Language Code Clone Detection
arXiv:2605.02860v1 Announce Type: new Abstract: Cross-language code clone detection (X-CCD) is challenging because semantically equivalent programs written in different languages often share little surface similarity. Although large language models (LLMs) have shown promise for semantic clone detection, their use as black-box systems raises concerns about cost, reproducibility, privacy, and unreliable output formatting. In particular, compact […]
Reinforcement Learning Trained Observer Control for Bearings-Only Tracking
arXiv:2605.02120v1 Announce Type: new Abstract: This paper develops a deep reinforcement learning based observer control policy for autonomous bearings-only tracking of a moving target. The observer manoeuvre problem is formulated as a belief Markov decision process, where the belief state is represented by the posterior of a cubature Kalman filter (CKF). The reward function is […]
An Empirical Study of Agent Skills for Healthcare: Practice, Gaps, and Governance
arXiv:2605.02709v1 Announce Type: new Abstract: Healthcare automation is shaped by local procedures and organizational constraints, so agent capabilities rarely transfer unchanged across settings. Agent skills, self-contained directories that package reusable procedures for AI agents, are emerging as a procedural layer for adapting healthcare agents across diverse healthcare settings. We present the first empirical analysis of […]