ThinkInAI Community
Jul 5, 2026 · Artificial Intelligence
Top AI Labs Converge: System Prompts as Reward Functions for RL Agents
This article traces the evolution from RLHF to RLVR and introduces RULER, a general reward function that uses LLM-as-judge to score agent trajectories against system prompts, enabling RL for non-verifiable tasks like RAG and tool use, with code examples from OpenPipe's ART framework.
GRPOLLMOpenPipe ART
0 likes · 40 min read
