https://venturebeat.com/orchestration/new-mit-and-sakana-ai-framework-uses-an-llm-judge-to-cut-evaluation-costs-for-self-improving-coding-agentsVentureBeaten2026-10-02T22:50:08.168+00:00New MIT and Sakana AI framework uses an LLM judge to cut evaluation costs for self-improving coding agentshttps://images.ctfassets.net/jdtwqhzvc2n1/1J7M5sir7llu69q7cACSLv/3c39a40723a1e4a6665cb9ded1dcb812/Branching_self-improving_AI_agent.png?w=300&q=30