arXiv:2601.19834v1 Announce Type: new Abstract: Humans construct internal world models and reason by manipulating the concepts within these models. Recent advances in AI, particularly chain-of-thought (CoT) reasoning, approximate such human cognitive abilities, where world models are believed to be embedded within large language models. Expert-level performance in formal and abstract domains such as mathematics and […]
Agentic Digital Twins: A Taxonomy of Capabilities for Understanding Possible Futures
arXiv:2601.18799v1 Announce Type: cross Abstract: As digital twins (DTs) evolve to become more agentic through the integration of artificial intelligence (AI), they acquire capabilities that extend beyond dynamic representation of their target systems. This paper presents a taxonomy of agentic DTs organised around three fundamental dimensions: the locus of agency (external, internal, distributed), the tightness […]
ComAgent: Multi-LLM based Agentic AI Empowered Intelligent Wireless Networks
arXiv:2601.19607v1 Announce Type: new Abstract: Emerging 6G networks rely on complex cross-layer optimization, yet manually translating high-level intents into mathematical formulations remains a bottleneck. While Large Language Models (LLMs) offer promise, monolithic approaches often lack sufficient domain grounding, constraint awareness, and verification capabilities. To address this, we present ComAgent, a multi-LLM agentic AI framework. ComAgent […]
GAVEL: Towards rule-based safety through activation monitoring
arXiv:2601.19768v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly paired with activation-based monitoring to detect and prevent harmful behaviors that may not be apparent at the surface-text level. However, existing activation safety approaches, trained on broad misuse datasets, struggle with poor precision, limited flexibility, and lack of interpretability. This paper introduces a new […]
Prompt-Counterfactual Explanations for Generative AI System Behavior
arXiv:2601.03156v2 Announce Type: replace-cross Abstract: As generative AI systems become integrated into real-world applications, organizations increasingly need to be able to understand and interpret their behavior. In particular, decision-makers need to understand what causes generative AI systems to exhibit specific output characteristics. Within this general topic, this paper examines a key question: what is it […]
Reinforcement Learning for Quantum Technology
arXiv:2601.18953v1 Announce Type: cross Abstract: Many challenges arising in Quantum Technology can be successfully addressed using a set of machine learning algorithms collectively known as reinforcement learning (RL), based on adaptive decision-making through interaction with the quantum device. After a concise and intuitive introduction to RL aimed at a broad physics readership, we discuss the […]
Improving Implicit Hate Speech Detection via a Community-Driven Multi-Agent Framework
arXiv:2601.09342v2 Announce Type: replace-cross Abstract: This work proposes a contextualised detection framework for implicitly hateful speech, implemented as a multi-agent system comprising a central Moderator Agent and dynamically constructed Community Agents representing specific demographic groups. Our approach explicitly integrates socio-cultural context from publicly available knowledge sources, enabling identity-aware moderation that surpasses state-of-the-art prompting methods (zero-shot […]
SynCABEL: Synthetic Contextualized Augmentation for Biomedical Entity Linking
arXiv:2601.19667v1 Announce Type: cross Abstract: We present SynCABEL (Synthetic Contextualized Augmentation for Biomedical Entity Linking), a framework that addresses a central bottleneck in supervised biomedical entity linking (BEL): the scarcity of expert-annotated training data. SynCABEL leverages large language models to generate context-rich synthetic training examples for all candidate concepts in a target knowledge base, providing […]
ProToken: Token-Level Attribution for Federated Large Language Models
arXiv:2601.19672v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative training of Large Language Models (LLMs) across distributed data sources while preserving privacy. However, when federated LLMs are deployed in critical applications, it remains unclear which client(s) contributed to specific generated responses, hindering debugging, malicious client identification, fair reward allocation, and trust verification. We present […]
De novo emergence of metabolically active protocells
arXiv:2601.11013v2 Announce Type: replace-cross Abstract: A continuous route from a disordered soup of simple chemical feedstocks to a functional protocell — a compartment that metabolizes, grows, and propagates — remains elusive. Here, we show that a homogeneous aqueous chemical mixture containing phosphorus, iron, molybdenum salts and formaldehyde spontaneously self-organizes into compartments that couple robust non-equilibrium […]
A Benchmark for Audio Reasoning Capabilities of Multimodal Large Language Models
arXiv:2601.19673v1 Announce Type: cross Abstract: The present benchmarks for testing the audio modality of multimodal large language models concentrate on testing various audio tasks such as speaker diarization or gender identification in isolation. Whether a multimodal model can answer the questions that require reasoning skills to combine audio tasks of different categories, cannot be verified […]
Representational Homomorphism Predicts and Improves Compositional Generalization In Transformer Language Model
arXiv:2601.18858v1 Announce Type: cross Abstract: Compositional generalization-the ability to interpret novel combinations of familiar components-remains a persistent challenge for neural networks. Behavioral evaluations reveal when models fail but offer limited insight into why failures arise at the representational level. We introduce Homomorphism Error (HE), a structural metric that quantifies deviations from approximate homomorphisms between the […]