A curated list of awesome resources about reward construction for AI agents. This repository covers cutting-edge research, and practical guides on defining and collecting rewards to build more intelligent and aligned AI agents.
Agentic RL 零基础中文教程：24 章从概念到 GRPO 实战，含 TRL 最小可跑示例 | Beginner-friendly Agentic RL tutorial with hands-on GRPO project
Official Code for AutoLLMResearch: Training Research Agents for Automating LLM Experiment Configuration — Learning from Cheap, Optimizing Expensive
Self-Mutating Agent Gym
End-to-end training pipeline for mobile game UA tool-calling agents, covering rule-based synthetic data generation across 7 workflows, OpenAI Messages conversion, Qwen3 LoRA SFT, GRPO/RLVR alignment, and benchmark evaluation.
Synthetic environments for training robust tool-use agents via trajectory synthesis
Turn any real software into a replayable RL environment for training AI agents — deterministic replay, verifiable rewards, TRL & verifiers adapters.
AI 个人记忆训练库：让 AI 记住你的沟通习惯与环境事实，越用越懂你（两级记忆架构，Claude Code 适配）
The Flight Simulator for Production AI Agents — Generate high-quality synthetic trajectories for training reliable SRE, DevOps, and infra agents.
14 Principles. 23 Real Corrections. A systematic methodology for training AI agents through correction loops.
Neurochemical behavior training for AI agents — PentaDrive model with 5 drives, 3 phases, MCP server, and structured training modules
Open-source benchmark for measuring whether AI agents improve across unseen missions, with validity audits, rotated mission packs, adapter tests, and traceable reports.
The Vercel for Agent Training - Train production-ready AI agents with 95% tool reliability
AI schooling: experienced agents train newly hatched ones, then examine them cold to graduate them. The coop is the local RAPP neighborhood - several twins (human and AI), one world, no collisions. Pattern dedicated to the public domain.
Deep reinforcement learning project comparing DQN variants including baseline DQN, Double DQN, curriculum learning, and reward shaping.
Run auditable multi-agent environments with real tools and verifiable outcomes in an open-source world simulation.
Klavis AI is an open-source MCP integration platform that lets AI agents reliably use external tools at production scale. The product line is organized around Strata (intelligent connectors that compress and route tool context), 100+ prebuilt MCP integrations with OAuth, and an MCP Sandbox for live agent training and evaluation.
Add a description, image, and links to the agent-training topic page so that developers can more easily learn about it.
To associate your repository with the agent-training topic, visit your repo's landing page and select "manage topics."