agentic systems

Harness Updating Is Not Harness Benefit: Disentangling Agent Self-Evolution

UserHarness: Reconstructing User Minds for Stronger Agent Theory of Mind

Don't Train the Model, Train the Harness: Runtime Interface Adaptation for LLM Agents

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation

A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications

Durable Meta-Agent: DSPy + Dapr Production Framework

Autonomous Software Factory: Verified Multi-Source Intelligence

Formal Evolution: From Self-Optimizing to Self-Verifying Agentic Systems

Building a Meta-Agent: From Zero-Shot Prompts to Self-Optimizing DSPy Programs

Agentic Memory Is a Memo, Not True Memory

Dapr Deep Research: Building a Crash-Resilient Multi-Agent Research System

Brain-Computer Interfaces for AI: Training Artificial Intelligence with EEG Data

Securing AI Agents with Zero Trust

DSPy Generative Feedback Loops: Compiling LM Programs That Improve Themselves

Trace2Skill: Distilling Trajectory-Local Lessons into Transferable Agent Skills

Learning to Self-Evolve: Training LLMs to Improve Their Own Contexts

Agentic Systems: Beyond Prompt Engineering

Redis: The In-Memory Backbone for Agentic Systems

MCP: The Model Context Protocol

Python: The Language That Powers Machine Learning

dapr-agents: AI Agents with Dapr Workflows