digitado

arXiv:2604.04990v1 Announce Type: new Abstract: 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 […]

Ver mais

arXiv:2604.04989v1 Announce Type: new Abstract: LLM-based agent systems increasingly rely on agent skills sourced from open registries to extend their capabilities, yet the openness of such ecosystems makes skills difficult to thoroughly vet. Existing attacks rely on injecting malicious instructions into skills, making them easily detectable by static auditing. However, non-malicious skills may also harbor latent vulnerabilities that an attacker can exploit solely through adversarial prompting, without modifying the skill itself. We introduce SkillAttack, a red-teaming framework that […]

Ver mais

arXiv:2604.04988v1 Announce Type: new Abstract: Modern deployment often requires trading accuracy for efficiency under tight CPU and memory constraints, yet common compression proxies such as parameter count or FLOPs do not reliably predict wall-clock inference time. In particular, unstructured sparsity can reduce model storage while failing to accelerate (and sometimes slightly slowing down) standard CPU execution due to irregular memory access and sparse kernel overhead. Motivated by this gap between compression and acceleration, we study a practical, ordered […]

Ver mais

arXiv:2604.04986v1 Announce Type: new Abstract: Model-free deep reinforcement learning (DRL) methods suffer from poor sample efficiency. To overcome this limitation, this work introduces an adaptive reduced-order-model (ROM)-based reinforcement learning framework for active flow control. In contrast to conventional actor–critic architectures, the proposed approach leverages a ROM to estimate the gradient information required for controller optimization. The design of the ROM structure incorporates physical insights. The ROM integrates a linear dynamical system and a neural ordinary differential equation (NODE) […]

Ver mais

arXiv:2604.04984v1 Announce Type: new Abstract: This work studies a variational formulation and numerical solution of a regularized morphoelasticity problem of shape evolution. The foundation of our analysis is based on the governing equations of linear elasticity, extended to account for volumetric growth. In the morphoelastic framework, the total deformation is decomposed into an elastic component and a growth component, represented by a growth tensor $G$. While the forward one-step problem — computing displacement given a growth tensor — […]

Ver mais

arXiv:2604.04983v1 Announce Type: new Abstract: We present Territory Paint Wars, a minimal competitive multi-agent reinforcement learning environment implemented in Unity, and use it to systematically investigate failure modes of Proximal Policy Optimisation (PPO) under self-play. A first agent trained for $84{,}000$ episodes achieves only $26.8%$ win rate against a uniformly-random opponent in a symmetric zero-sum game. Through controlled ablations we identify five implementation-level failure modes — reward-scale imbalance, missing terminal signal, ineffective long-horizon credit assignment, unnormalised observations, and […]

Ver mais

arXiv:2604.04982v1 Announce Type: new Abstract: 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 […]

Ver mais

arXiv:2604.04980v1 Announce Type: new Abstract: Experimental access to real honeybee colonies requires robotic systems capable of operating within limited spatial constraints, tolerating hive-specific fouling and environmental conditions, and supporting both sensing and localized actuation without frequent hardware redesign. This paper introduces COMB, a compact, open-source, modular mechatronic platform designed for in-hive experiments within standard observation-hive frames. The platform integrates a XY positioning stage, a Movable Access Window (MAW) for sealed tool access through the hive boundary, interchangeable payload […]

Ver mais

arXiv:2604.04979v1 Announce Type: new Abstract: 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 […]

Ver mais

arXiv:2604.04978v1 Announce Type: new Abstract: Claude Code’s auto mode is the first deployed permission system for AI coding agents, using a two-stage transcript classifier to gate dangerous tool calls. Anthropic reports a 0.4% false positive rate and 17% false negative rate on production traffic. We present the first independent evaluation of this system on deliberately ambiguous authorization scenarios, i.e., tasks where the user’s intent is clear but the target scope, blast radius, or risk level is underspecified. Using […]

Ver mais