Search

An autonomous AI scientist: a multi-agent loop over literature, experiments, self-critique and write-up, with deterministic guards against reward-hacking and hallucination.

Comprehensive toolkit for Reinforcement Learning from Human Feedback (RLHF) training, featuring instruction fine-tuning, reward model training, and support for PPO and DPO algorithms with various configurations for the Transformer 5 models including Qwen 3.0

A reward-based habit tracker for android.

SQL-o1: A Self-Reward Heuristic Dynamic Search Method for Text-to-SQL

A comprehensive collection of process reward models.

Braincraft challenge — 1000 neurons, 100 seconds, 10 runs, 2 choices, no reward

[ICLR 2026] On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification.

[CVPR 2026] Official Code for "ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning"

[CVPR 2026] Official implementation of "Robo-Dopamine: General Process Reward Modeling for High-Precision Robotic Manipulation"

Official repository for the paper "Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation"

Intelligent Skill routing and workflow orchestration for AI agents — +21.12 pp reward, −29.6% tokens on SkillsBench with DeepSeekV4Flash-VE.

You're reading this. The skill predicted it. A workflow that turns every post into a calibrated experiment—score, blind-predict, retro, evolve. The future doesn't reward effort, it rewards those who see the pattern first. 1M followers in a month — not luck, system.

Automated Discord Quest Reward Collector Tool 2026

Long Horizon Terminal Benchmark with Dense Reward Grading

LLM-authored task-specific Jev harnesses with optional full-trajectory reward reflection and GEPA evolution.