digitado

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

arXiv:2604.04977v1 Announce Type: new Abstract: 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 […]

Ver mais

arXiv:2604.04976v1 Announce Type: new Abstract: Generative recommender systems are rapidly emerging as a new paradigm for recommendation, where collaborative identifiers and/or multi-modal content are mapped into discrete token spaces and user behavior is modelled with autoregressive sequence models. Despite progress on multi-modal recommendation datasets, there is still a lack of public benchmarks that jointly offer large-scale, realistic and fully all-modality data designed specifically for generative recommendation (GR) in industrial advertising. To foster research in this direction, we organised […]

Ver mais

arXiv:2604.04974v1 Announce Type: new Abstract: Video is a scalable observation of physical dynamics: it captures how objects move, how contact unfolds, and how scenes evolve under interaction — all without requiring robot action labels. Yet translating this temporal structure into reliable robotic control remains an open challenge, because video lacks action supervision and differs from robot experience in embodiment, viewpoint, and physical constraints. This survey reviews methods that exploit non-action-annotated temporal video to learn control interfaces for robotic […]

Ver mais

arXiv:2604.04972v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) suffer from prohibitive inference costs due to the massive number of visual tokens processed by the language decoder. Existing pruning methods often lead to significant performance degradation because the irreversible removal of visual tokens causes a distribution shift in the hidden states that deviates from the pre-trained full-token regime. To address this, we propose Representation Consistency Pruner, which we refer to as RCP, as a novel framework that integrates […]

Ver mais

arXiv:2604.04971v1 Announce Type: new Abstract: While Physics-Informed Neural Networks offer a promising framework for solving partial differential equations, the standard $L^2$ loss formulation is fundamentally insufficient when applied to the Bhatnagar-Gross-Krook (BGK) model. Specifically, simply minimizing the standard loss does not guarantee accurate predictions of the macroscopic moments, causing the approximate solutions to fail in capturing the true physical solution. To overcome this limitation, we introduce a velocity-weighted $L^2$ loss function designed to effectively penalize errors in the […]

Ver mais

arXiv:2604.04969v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) mitigates hallucinations in Multimodal Large Language Models (MLLMs), yet existing systems struggle with complex cross-modal reasoning. Flat vector retrieval often ignores structural dependencies, while current graph-based methods rely on costly “translation-to-text” pipelines that discard fine-grained visual information. To address these limitations, we propose textbf{MG$^2$-RAG}, a lightweight textbf{M}ulti-textbf{G}ranularity textbf{G}raph textbf{RAG} framework that jointly improves graph construction, modality fusion, and cross-modal retrieval. MG$^2$-RAG constructs a hierarchical multimodal knowledge graph by combining lightweight […]

Ver mais

arXiv:2604.04967v1 Announce Type: new Abstract: Robots operating in shared workspaces must maintain safe coordination with other agents whose behavior may change during task execution. When a collaborating agent switches strategy mid-episode, continuing under outdated assumptions can lead to unsafe actions and increased collision risk. Reliable detection of such behavioral regime changes is therefore critical. We study regime-switch detection under controlled non-stationarity in ManiSkill shared-workspace manipulation tasks. Across ten detection methods and five random seeds, enabling detection reduces post-switch […]

Ver mais

arXiv:2604.04962v1 Announce Type: new Abstract: We present a general framework for constructing structure-preserving numerical integrators for nonholonomically constrained mechanical systems evolving on Lie groups using retraction maps. Retraction maps generalize the exponential map and provide a convenient tool for performing numerical integration on manifolds. In nonholonomic mechanics, the constraints restrict the dynamics to a nonintegrable distribution rather than the entire tangent bundle. Using the Hamel formulation, the equations of motion can be expressed in local coordinates adapted to […]

Ver mais