Frustratingly Easy Agentic RAG via Portable Skills: A Case Study in Customer Support

arXiv:2610.14428 · cs.AI · Submitted 2026-10-10 · Read on arXiv

cs.AI

Submitted: 2026-10-10

Updated: 2026-10-10

Comments: Accepted to EMNLP 2026 Industry Track. 15 pages, 1 figure, 5 tables

Code: https://github.com/karpathy/442a6b

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• RAG — 1× in this paper · explained in 3 episodes

Sources

• From Local to Global: A Graph RAG Approach to Query-Focused Summarization
• Retrieval-Augmented Generation for Large Language Models: A Survey
• Document Expansion by Query Prediction
• Large Language Models are Inconsistent and Biased Evaluators

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems