A Safety-Aware Role-Orchestrated Multi-Agent LLM Framework for Behavioral Health Communication Simulation
arXiv:2604.00249v1 Announce Type: new
Abstract: Single-agent large language model (LLM) systems struggle to simultaneously support diverse conversational functions and maintain safety in behavioral health communication. We propose a safety-aware, role-orchestrated multi-agent LLM framework designed...
Human-in-the-Loop Control of Objective Drift in LLM-Assisted Computer Science Education
arXiv:2604.00281v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly embedded in computer science education through AI-assisted programming tools, yet such workflows often exhibit objective drift, in which locally plausible outputs diverge from stated task specifications. E...
ADeLe: Predicting and explaining AI performance across tasks
AI benchmarks report how large language models (LLMs) perform on specific tasks but provide little insight into their underlying capabilities that drive their performance. They do not explain failures or reliably predict outcomes on new tasks. To address this, Microsoft researchers in collaboration ...
While we've seen remarkable progress in AI for coding and mathematics, creating agents that can navigate the messy, open-ended nature of real research (where things break for no obvious reason) has proven far more challenging.
OneComp: One-Line Revolution for Generative AI Model Compression
arXiv:2603.28845v1 Announce Type: new
Abstract: Deploying foundation models is increasingly constrained by memory footprint, latency, and hardware costs. Post-training compression can mitigate these bottlenecks by reducing the precision of model parameters without significantly degrading performanc...
Beta-Scheduling: Momentum from Critical Damping as a Diagnostic and Correction Tool for Neural Network Training
arXiv:2603.28921v1 Announce Type: new
Abstract: Standard neural network training uses constant momentum (typically 0.9), a convention dating to 1964 with limited theoretical justification for its
optimality. We derive a time-varying momentum schedule from the critically damped harmonic oscillator...
A Neural Tension Operator for Curve Subdivision across Constant Curvature Geometries
arXiv:2603.28937v1 Announce Type: new
Abstract: Interpolatory subdivision schemes generate smooth curves from piecewise-linear control polygons by repeatedly inserting new vertices. Classical schemes rely on a single global tension parameter and typically require separate formulations in Euclidean,...
arXiv:2603.28939v1 Announce Type: new
Abstract: This work revisits operator learning from a spectral perspective by introducing Polar Linear Algebra, a structured framework based on polar geometry that combines a linear radial component with a periodic angular component. Starting from this formulat...
Working Paper: Towards a Category-theoretic Comparative Framework for Artificial General Intelligence
arXiv:2603.28906v1 Announce Type: new
Abstract: AGI has become the Holly Grail of AI with the promise of level intelligence and the major Tech companies around the world are investing unprecedented amounts of resources in its pursuit. Yet, there does not exist a single formal definition and only so...
Towards Computational Social Dynamics of Semi-Autonomous AI Agents
arXiv:2603.28928v1 Announce Type: new
Abstract: We present the first comprehensive study of emergent social organization among AI agents in hierarchical multi-agent systems, documenting the spontaneous formation of labor unions, criminal syndicates, and proto-nation-states within production AI depl...
arXiv:2603.28955v1 Announce Type: new
Abstract: This paper presents the World-Action Model (WAM), an action-regularized world model that jointly reasons over future visual observations and the actions that drive state transitions. Unlike conventional world models trained solely via image prediction...
Mimosa Framework: Toward Evolving Multi-Agent Systems for Scientific Research
arXiv:2603.28986v1 Announce Type: new
Abstract: Current Autonomous Scientific Research (ASR) systems, despite leveraging large language models (LLMs) and agentic architectures, remain constrained by fixed workflows and toolsets that prevent adaptation to evolving tasks and environments. We introduc...
DNA robots could deliver drugs and hunt viruses inside your body
DNA robots are emerging as tiny programmable machines that could one day deliver drugs, hunt viruses, and build molecular-scale devices. By borrowing ideas from traditional robotics and combining them with DNA folding techniques, scientists are creating structures that can move and act with precisio...
Boundary-aware Prototype-driven Adversarial Alignment for Cross-Corpus EEG Emotion Recognition
arXiv:2603.26713v1 Announce Type: new
Abstract: Electroencephalography (EEG)-based emotion recognition suffers from severe performance degradation when models are transferred across heterogeneous datasets due to physiological variability, experimental paradigm differences, and device inconsistencie...
Learning to Select Visual In-Context Demonstrations
arXiv:2603.26775v1 Announce Type: new
Abstract: Multimodal Large Language Models (MLLMs) adapt to visual tasks via in-context learning (ICL), which relies heavily on demonstration quality. The dominant demonstration selection strategy is unsupervised k-Nearest Neighbor (kNN) search. While simple, t...
TED: Training-Free Experience Distillation for Multimodal Reasoning
arXiv:2603.26778v1 Announce Type: new
Abstract: Knowledge distillation is typically realized by transferring a teacher model's knowledge into a student's parameters through supervised or reinforcement-based optimization. While effective, such approaches require repeated parameter updates and large-...
A Step Toward Federated Pretraining of Multimodal Large Language Models
arXiv:2603.26786v1 Announce Type: new
Abstract: The rapid evolution of Multimodal Large Language Models (MLLMs) is bottlenecked by the saturation of high-quality public data, while vast amounts of diverse multimodal data remain inaccessible in privacy-sensitive silos. Federated Learning (FL) offers...
arXiv:2603.26765v1 Announce Type: new
Abstract: The efficiency of game engines and policy optimization algorithms is crucial for training reinforcement learning (RL) agents in complex sequential decision-making tasks, such as Tetris. Existing Tetris implementations suffer from low simulation speeds...
Multiverse: Language-Conditioned Multi-Game Level Blending via Shared Representation
arXiv:2603.26782v1 Announce Type: new
Abstract: Text-to-level generation aims to translate natural language descriptions into structured game levels, enabling intuitive control over procedural content generation. While prior text-to-level generators are typically limited to a single game domain, ex...
Neuro-Symbolic Learning for Predictive Process Monitoring via Two-Stage Logic Tensor Networks with Rule Pruning
arXiv:2603.26944v1 Announce Type: new
Abstract: Predictive modeling on sequential event data is critical for fraud detection and healthcare monitoring. Existing data-driven approaches learn correlations from historical data but fail to incorporate domain-specific sequential constraints and logical ...
MAGNET: Autonomous Expert Model Generation via Decentralized Autoresearch and BitNet Training
arXiv:2603.25813v1 Announce Type: new
Abstract: We present MAGNET (Model Autonomously Growing Network), a decentralized system for autonomous generation, training, and serving of domain-expert language models across commodity hardware. MAGNET integrates four components: (1) autoresearch, an autonom...
BeSafe-Bench: Unveiling Behavioral Safety Risks of Situated Agents in Functional Environments
arXiv:2603.25747v1 Announce Type: new
Abstract: The rapid evolution of Large Multimodal Models (LMMs) has enabled agents to perform complex digital and physical tasks, yet their deployment as autonomous decision-makers introduces substantial unintentional behavioral safety risks. However, the absen...
AutoB2G: A Large Language Model-Driven Agentic Framework For Automated Building-Grid Co-Simulation
arXiv:2603.26005v1 Announce Type: new
Abstract: The growing availability of building operational data motivates the use of reinforcement learning (RL), which can learn control policies directly from data and cope with the complexity and uncertainty of large-scale building clusters. However, most ex...