arXiv:2604.05634v1 Announce Type: new Abstract: Machine unlearning (MU) has become a critical technique for GenAI models’ safe and compliant operation. While existing MU methods are effective, most impose prohibitive training time and computational overhead. Our analysis suggests the root cause lies in poorly directed gradient updates, which reduce training efficiency and destabilize convergence. To mitigate […]
Can Large Language Models Reinvent Foundational Algorithms?
arXiv:2604.05716v1 Announce Type: new Abstract: LLMs have shown strong potential to advance scientific discovery. Whether they possess the capacity for foundational innovation, however, remains an open question. In this work, we focus on a prerequisite for foundational innovation: can LLMs reinvent foundational algorithms in computer science? Our textitUnlearn-and-Reinvent pipeline applies LLM unlearning to remove a […]
Hierarchical Reinforcement Learning with Augmented Step-Level Transitions for LLM Agents
arXiv:2604.05808v1 Announce Type: new Abstract: Large language model (LLM) agents have demonstrated strong capabilities in complex interactive decision-making tasks. However, existing LLM agents typically rely on increasingly long interaction histories, resulting in high computational cost and limited scalability. In this paper, we propose STEP-HRL, a hierarchical reinforcement learning (HRL) framework that enables step-level learning by […]
When Do We Need LLMs? A Diagnostic for Language-Driven Bandits
arXiv:2604.05859v1 Announce Type: new Abstract: We study Contextual Multi-Armed Bandits (CMABs) for non-episodic sequential decision making problems where the context includes both textual and numerical information (e.g., recommendation systems, dynamic portfolio adjustments, offer selection; all frequent problems in finance). While Large Language Models (LLMs) are increasingly applied to these settings, utilizing LLMs for reasoning at […]
How LLMs Follow Instructions: Skillful Coordination, Not a Universal Mechanism
arXiv:2604.06015v1 Announce Type: new Abstract: Instruction tuning is commonly assumed to endow language models with a domain-general ability to follow instructions, yet the underlying mechanism remains poorly understood. Does instruction-following rely on a universal mechanism or compositional skill deployment? We investigate this through diagnostic probing across nine diverse tasks in three instruction-tuned models. Our analysis […]
CRFT: Consistent-Recurrent Feature Flow Transformer for Cross-Modal Image Registration
arXiv:2604.05689v1 Announce Type: cross Abstract: We present Consistent-Recurrent Feature Flow Transformer (CRFT), a unified coarse-to-fine framework based on feature flow learning for robust cross-modal image registration. CRFT learns a modality-independent feature flow representation within a transformer-based architecture that jointly performs feature alignment and flow estimation. The coarse stage establishes global correspondences through multi-scale feature correlation, […]
Artificial Intelligence and the Structure of Mathematics
arXiv:2604.06107v1 Announce Type: new Abstract: Recent progress in artificial intelligence (AI) is unlocking transformative capabilities for mathematics. There is great hope that AI will help solve major open problems and autonomously discover new mathematical concepts. In this essay, we further consider how AI may open a grand perspective on mathematics by forging a new route, […]
Generative AI for Video Trailer Synthesis: From Extractive Heuristics to Autoregressive Creativity
arXiv:2604.04953v1 Announce Type: cross Abstract: The domain of automatic video trailer generation is currently undergoing a profound paradigm shift, transitioning from heuristic-based extraction methods to deep generative synthesis. While early methodologies relied heavily on low-level feature engineering, visual saliency, and rule-based heuristics to select representative shots, recent advancements in Large Language Models (LLMs), Multimodal Large […]
Flowr — Scaling Up Retail Supply Chain Operations Through Agentic AI in Large Scale Supermarket Chains
arXiv:2604.05987v1 Announce Type: new Abstract: Retail supply chain operations in supermarket chains involve continuous, high-volume manual workflows spanning demand forecasting, procurement, supplier coordination, and inventory replenishment, processes that are repetitive, decision-intensive, and difficult to scale without significant human effort. Despite growing investment in data analytics, the decision-making and coordination layers of these workflows remain predominantly […]
Contextuality as an External Bookkeeping Cost under Fixed Shared-State Semantics
arXiv:2601.20167v2 Announce Type: cross Abstract: Contextuality is a central feature distinguishing quantum from classical probability theories, but its operational meaning is often stated only qualitatively. In this Letter, we study a simple information-theoretic question: how much additional contextual information must a classical simulation introduce when it tries to keep a shared internal description fixed across […]
Automatic Image-Level Morphological Trait Annotation for Organismal Images
arXiv:2604.01619v2 Announce Type: replace-cross Abstract: Morphological traits are physical characteristics of biological organisms that provide vital clues on how organisms interact with their environment. Yet extracting these traits remains a slow, expert-driven process, limiting their use in large-scale ecological studies. A major bottleneck is the absence of high-quality datasets linking biological images to trait-level annotations. […]
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
arXiv:2604.06132v1 Announce Type: new Abstract: Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer from three critical limitations: (1) trajectory-opaque grading that checks only final outputs, (2) underspecified safety and robustness evaluation, and (3) narrow modality coverage and interaction paradigms. We introduce Claw-Eval, […]