AI Agents & Automation

Anthropic’s New TPU Deal, Anthropic’s Computing Crunch, The Anthropic-Google Alliance

Identifying Necessary Transparency Moments In Agentic AI (Part 1)

Anthropic Accidentally Exposes Claude Code Source via npm Source Map File

Google Open Sources Experimental Multi-Agent Orchestration Testbed Scion

Surviving Tech Debt: How 2,611 Golang Linter Issues Solved in 3 Days

ActionNex: A Virtual Outage Manager for Cloud

Explainable Model Routing for Agentic Workflows

Towards the AI Historian: Agentic Information Extraction from Primary Sources

Personality Requires Struggle: Three Regimes of the Baldwin Effect in Neuroevolved Chess Agents

Rashomon Memory: Towards Argumentation-Driven Retrieval for Multi-Perspective Agent Memory

Single-agent vs. Multi-agents for Automated Video Analysis of On-Screen Collaborative Learning Behaviors

RL-Driven Sustainable Land-Use Allocation for the Lake Malawi Basin

Decomposing Communication Gain and Delay Cost Under Cross-Timestep Delays in Cooperative Multi-Agent Reinforcement Learning

SKILLFOUNDRY: Building Self-Evolving Agent Skill Libraries from Heterogeneous Scientific Resources

Quantifying Trust: Financial Risk Management for Trustworthy AI Agents

Compliance-by-Construction Argument Graphs: Using Generative AI to Produce Evidence-Linked Formal Arguments for Certification-Grade Accountability

MC-CPO: Mastery-Conditioned Constrained Policy Optimization

Beyond Fluency: Toward Reliable Trajectories in Agentic IR

Soft Tournament Equilibrium

RoboPhD: Evolving Diverse Complex Agents Under Tight Evaluation Budgets

Gradual Cognitive Externalization: A Framework for Understanding How Ambient Intelligence Externalizes Human Cognition

GUIDE: Interpretable GUI Agent Evaluation via Hierarchical Diagnosis

ShieldNet: Network-Level Guardrails against Emerging Supply-Chain Injections in Agentic Systems

SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems

Receding-Horizon Control via Drifting Models

Greedy and Transformer-Based Multi-Port Selection for Slow Fluid Antenna Multiple Access

Same World, Differently Given: History-Dependent Perceptual Reorganization in Artificial Agents

AI Trust OS -- A Continuous Governance Framework for Autonomous AI Observability and Zero-Trust Compliance in Enterprise Environments

ANX: Protocol-First Design for AI Agent Interaction with a Supporting 3EX Decoupled Architecture

Learning, Potential, and Retention: An Approach for Evaluating Adaptive AI-Enabled Medical Devices

FVRuleLearner: Operator-Level Reasoning Tree (OP-Tree)-Based Rules Learning for Formal Verification

Personalized AI Practice Replicates Learning Rate Regularity at Scale

Artificial Intelligence and Systemic Risk: A Unified Model of Performative Prediction, Algorithmic Herding, and Cognitive Dependency in Financial Markets

Event-Driven Neuromorphic Vision Enables Energy-Efficient Visual Place Recognition

Safe Decentralized Operation of EV Virtual Power Plant with Limited Network Visibility via Multi-Agent Reinforcement Learning

Customized User Plane Processing via Code Generating AI Agents for Next Generation Mobile Networks

Toward Artificial Intelligence Enabled Earth System Coupling

RAGnaroX: A Secure, Local-Hosted ChatOps Assistant Using Small Language Models

AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting System

Downscaling weather forecasts from Low- to High-Resolution with Diffusion Models

AICCE: AI Driven Compliance Checker Engine

Composer Vector: Style-steering Symbolic Music Generation in a Latent Space

From Model-Based Screening to Data-Driven Surrogates: A Multi-Stage Workflow for Exploring Stochastic Agent-Based Models

Banana100: Breaking NR-IQA Metrics by 100 Iterative Image Replications with Nano Banana Pro

Generative AI for material design: A mechanics perspective from burgers to matter

AEGIS: Scaling Long-Sequence Homomorphic Encrypted Transformer Inference via Hybrid Parallelism on Multi-GPU Systems

VisionClaw: Always-On AI Agents through Smart Glasses

Inside the Scaffold: A Source-Code Taxonomy of Coding Agent Architectures