Pretraining with Hierarchical Memories: Separating Long-Tail and Common Knowledge
The impressive performance gains of modern language models currently rely on scaling parameters: larger models store more world knowledge and reason better. Yet compressing all world knowledge into parameters is unnecessary, as only a fraction is used per prompt, and impractical for edge devices wit...
Which Evaluation for Which Model? A Taxonomy for Speech Model Assessment
Speech foundation models have recently achieved remarkable capabilities across a wide range of tasks. However, their evaluation remains disjointed across tasks and model types. Different models excel at distinct aspects of speech processing and thus require different evaluation protocols. This paper...
AgentBuilder: Exploring Scaffolds for Prototyping User Experiences of Interface Agents
Interface agents powered by generative AI models (referred to as “agents”) can automate actions based on user commands. An important aspect of developing agents is their user experience (i.e., agent experience). There is a growing need to provide scaffolds for a broader set of individuals beyond AI ...
Lightweight Transformer Architectures for Edge Devices in Real-Time Applications
arXiv:2601.03290v1 Announce Type: new
Abstract: The deployment of transformer-based models on resource-constrained edge devices represents a critical challenge in enabling real-time artificial intelligence applications. This comprehensive survey examines lightweight transformer architectures specif...
Ratio-Variance Regularized Policy Optimization for Efficient LLM Fine-tuning
arXiv:2601.03320v1 Announce Type: new
Abstract: On-policy reinforcement learning (RL), particularly Proximal Policy Optimization (PPO) and Group Relative Policy Optimization (GRPO), has become the dominant paradigm for fine-tuning large language models (LLMs). While policy ratio clipping stabilizes...
Mastering the Game of Go with Self-play Experience Replay
arXiv:2601.03306v1 Announce Type: new
Abstract: The game of Go has long served as a benchmark for artificial intelligence, demanding sophisticated strategic reasoning and long-term planning. Previous approaches such as AlphaGo and its successors, have predominantly relied on model-based Monte-Carlo...
Digital Red Queen: Adversarial Program Evolution in Core War with LLMs
arXiv:2601.03335v1 Announce Type: new
Abstract: Large language models (LLMs) are increasingly being used to evolve solutions to problems in many domains, in a process inspired by biological evolution. However, unlike biological evolution, most LLM-evolution frameworks are formulated as static optim...
Enhancing LLM Instruction Following: An Evaluation-Driven Multi-Agentic Workflow for Prompt Instructions Optimization
arXiv:2601.03359v1 Announce Type: new
Abstract: Large Language Models (LLMs) often generate substantively relevant content but fail to adhere to formal constraints, leading to outputs that are conceptually correct but procedurally flawed. Traditional prompt refinement approaches focus on rephrasing...
Exploration Through Introspection: A Self-Aware Reward Model
arXiv:2601.03389v1 Announce Type: new
Abstract: Understanding how artificial agents model internal mental states is central to advancing Theory of Mind in AI. Evidence points to a unified system for self- and other-awareness. We explore this self-awareness by having reinforcement learning agents in...
Toward Maturity-Based Certification of Embodied AI: Quantifying Trustworthiness Through Measurement Mechanisms
arXiv:2601.03470v2 Announce Type: new
Abstract: We propose a maturity-based framework for certifying embodied AI systems through explicit measurement mechanisms. We argue that certifiable embodied AI requires structured assessment frameworks, quantitative scoring mechanisms, and methods for navigat...
Less than a trillionth of a second: Ultrafast UV light could transform communications and imaging
Researchers have built a new platform that produces ultrashort UV-C laser pulses and detects them at room temperature using atom-thin materials. The light flashes last just femtoseconds and can be used to send encoded messages through open space. The system relies on efficient laser generation and h...
arXiv:2601.02433v1 Announce Type: new
Abstract: Digital AI systems spanning large language models, vision models, and generative architectures that operate primarily in symbolic, linguistic, or pixel domains. They have achieved striking progress, but almost all of this progress lives in virtual spa...
WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks
arXiv:2601.02439v1 Announce Type: new
Abstract: We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning. WebGym contains ...
Polynomial Convergence of Riemannian Diffusion Models
arXiv:2601.02499v1 Announce Type: new
Abstract: Diffusion models have demonstrated remarkable empirical success in the recent years and are considered one of the state-of-the-art generative models in modern AI. These models consist of a forward process, which gradually diffuses the data distributio...
GEM-Style Constraints for PEFT with Dual Gradient Projection in LoRA
arXiv:2601.02500v1 Announce Type: new
Abstract: Full fine-tuning of Large Language Models (LLMs) is computationally costly, motivating Continual Learning (CL) approaches that utilize parameter-efficient adapters. We revisit Gradient Episodic Memory (GEM) within the Low-Rank Adapter (LoRA) subspace ...
Textual Explanations and Their Evaluations for Reinforcement Learning Policy
arXiv:2601.02514v1 Announce Type: new
Abstract: Understanding a Reinforcement Learning (RL) policy is crucial for ensuring that autonomous agents behave according to human expectations. This goal can be achieved using Explainable Reinforcement Learning (XRL) techniques. Although textual explanation...
SimpleMem: Efficient Lifelong Memory for LLM Agents
arXiv:2601.02553v1 Announce Type: new
Abstract: To support reliable long-term interaction in complex environments, LLM agents require memory systems that efficiently manage historical experiences. Existing approaches either retain full interaction histories via passive context extension, leading to...
Orchestral AI: A Framework for Agent Orchestration
arXiv:2601.02577v1 Announce Type: new
Abstract: The rapid proliferation of LLM agent frameworks has forced developers to choose between vendor lock-in through provider-specific SDKs and complex multi-package ecosystems that obscure control flow and hinder reproducibility. Integrating tool calling a...
AWARE-US: Benchmark for Preference-Aware Resolution in Tool-Calling Agents
arXiv:2601.02643v1 Announce Type: new
Abstract: Tool-calling conversational agents querying structured databases often face two linked failures: underspecification (missing constraints needed to run a precise query) and infeasibility (the fully specified query returns an empty set because no item s...
Scientists create robots smaller than a grain of salt that can think
Researchers have created microscopic robots so small they’re barely visible, yet smart enough to sense, decide, and move completely on their own. Powered by light and equipped with tiny computers, the robots swim by manipulating electric fields rather than using moving parts. They can detect tempera...
ShrimpXNet: A Transfer Learning Framework for Shrimp Disease Classification with Augmented Regularization, Adversarial Training, and Explainable AI
arXiv:2601.00832v1 Announce Type: new
Abstract: Shrimp is one of the most widely consumed aquatic species globally, valued for both its nutritional content and economic importance. Shrimp farming represents a significant source of income in many regions; however, like other forms of aquaculture, it...
Intrinsic-Metric Physics-Informed Neural Networks (IM-PINN) for Reaction-Diffusion Dynamics on Complex Riemannian Manifolds
arXiv:2601.00834v1 Announce Type: new
Abstract: Simulating nonlinear reaction-diffusion dynamics on complex, non-Euclidean manifolds remains a fundamental challenge in computational morphogenesis, constrained by high-fidelity mesh generation costs and symplectic drift in discrete time-stepping sche...
Agentic AI for Autonomous, Explainable, and Real-Time Credit Risk Decision-Making
arXiv:2601.00818v1 Announce Type: new
Abstract: Significant digitalization of financial services in a short period of time has led to an urgent demand to have autonomous, transparent and real-time credit risk decision making systems. The traditional machine learning models are effective in pattern ...
CogCanvas: Compression-Resistant Cognitive Artifacts for Long LLM Conversations
arXiv:2601.00821v1 Announce Type: new
Abstract: Large language models face a fundamental tension between context window limits and information fidelity in long conversations. Existing approaches--truncation and summarization--either discard early information or lose nuanced details. We introduce Co...