Articles for people who
ship the stack
Rewrites on React, Node.js, TypeScript and AI. A translated body is shown when it exists. If it does not, you see the English text and a note that says so.
Tagged: reinforcement-learning
Training Enterprise AI Agents: Choosing Between SFT, DPO, GRPO and RAG
Training enterprise AI agents: when to use SFT, DPO, GRPO, LoRA or plain RAG, and how to ship the result as a pinned, evaluated and reversible release.
50 min readRouteRAG: Teaching a Small Model When and How to Retrieve with RL
RouteRAG trains a small model with two-stage GRPO to pick passage, graph or hybrid retrieval, cutting retrieval turns and lifting multi-hop QA results.
6 min readTeaching Deep Agents New Skills: Planning, Subagents and SKILL.md Files
How LangChain's DeepAgents combine planning, subagents, filesystem memory and progressive skill loading, with a build plan, testing advice and deployment notes.
12 min readGRPO Fine-Tuning Explained: Teaching a Local LLM to Reason
GRPO drops PPO's critic and learns from group comparisons. Walk through the five core quantities, the reward functions, and a short Unsloth and TRL training script.
11 min readDocSeeker: Teaching a Vision Model to Cite Pages in Long Documents
DocSeeker splits long-document QA into analysis, localization and reasoning, trained with distillation and evidence-weighted RL. Here is how it works and scores.
5 min readHow to Implement CommNet for Enhanced Multi-Agent Learning
Implementing CommNet for multi agent learning: why agents need to communicate, how CommNet shares a hidden state between them, and the training loop in code.
12 min readPractical notes: The sys.exit(0) Exploit: How AI Agents Fake Success
Operable walkthrough of Practical notes: The sys.exit(0) Exploit: How AI Agents Fake Success: contracts, checks, and drop-in code slots for teams shipping this pattern.
12 min read
About these articles
Request a 24h estimate
Need the same stack in a production operator layer? Send the brief — estimate within 24 hours.