ETH Zurich Study Proves Your AI Coding Agents are Failing Because Your AGENTS.md Files....

Here is your today’s AI Dev Brief from Marktechpost, covering core research, models, infrastructure tools, and applied updates for AI developers and researchers. Also, don’t forget to register for NVIDIA GTC 2026 event (In person/Virtual). NVIDIA has been supporting us to bring free and unlocked AI research and dev news content to you.

A comprehensive study by researchers at ETH Zurich has revealed that the popular practice of using repository-level context files like AGENTS.md often hinders rather than helps AI coding agents. The research found that LLM-generated context files actually reduce task success rates by approximately 3% while simultaneously increasing inference costs by over 20% due to unnecessary requirements and redundant information. While human-written context files can offer a marginal performance gain of about 4%, detailed codebase overviews and auto-generated content frequently distract agents, leading to broader but less efficient exploration. To optimize performance, AI devs should shift toward ‘minimal effective context,’ prioritizing high-level intent and non-obvious tooling instructions—which see a usage multiplier of up to 160x—while avoiding the "token tax" of redundant directory listings and style guides........… Read the full analysis/article here.

LM Link is a game-changing product from LM Studio and Tailscale that effectively turns your high-end GPU workstation into a private, encrypted AI cloud. By integrating tsnet directly into the architecture, the tool creates a secure, identity-based tunnel that allows you to run massive models on remote hardware as if they were plugged into your local machine—no public endpoints, no firewall tinkering, and zero "API key sprawl." The workflow is dead simple: you query localhost:1234 on your laptop, and LM Link handles the heavy lifting via a point-to-point WireGuard® connection to your "Big Rig" at home. It’s the ultimate fix for the "Big Model, Small Laptop" dilemma, providing data-center performance with local-level privacy...........… Read the full analysis/article here.

▶ Meet CopilotKit: Framework for building agent-native applications with Generative UI, shared state, and human-in-the-loop workflows Codes

▶ How to Build a Production-Grade Customer Support Automation Pipeline with Griptape Using Deterministic Tools and Agentic Reasoning Codes Tutorial

▶ How to Build a Fully Autonomous Local Fleet-Maintenance Analysis Agent Using SmolAgents and Qwen Model Codes Tutorial

▶ How to Build a Proactive Pre-Emptive Churn Prevention Agent with Intelligent Observation and Strategy Formation Codes Tutorial

▶ A Coding Guide to Design a Complete Agentic Workflow in Gemini for Automated Medical Evidence Gathering and Prior Authorization Submission Codes Tutorial

150+ more open codes/notebooks here ➡️