Nous Research Open-Sources GEPA for Self-Evolving AI Agent Prompts
Nous Research releases GEPA, an ICLR 2026 Oral paper engine that lets AI agents evolve prompts, using 35× less data than RL and boosting performance by 20%.
Nous Research have a codebase that enables AI agents to evolve their own prompts.
The core engine is called GEPA; the paper has been accepted to ICLR 2026 (Oral). It uses 35× less data than reinforcement learning while delivering 20% higher performance.
Comments
Weekly digest
The best of vibe coding, AI agents and open source — once a week, no spam.
Related articles
All articlesDigUp: EmbeddingGemma 2 Powered Local Search App for macOS
DigUp uses Google’s open‑source EmbeddingGemma 2 to deliver fast, on‑device search of files, PDFs, photos, podcasts and videos on macOS.
OpenAI expands GPT‑6.1 context window to 500k tokens by default
OpenAI raised the default context window of GPT‑6.1 in Codex and ChatGPT Work from 272k to 500k tokens, with plans for further expansion.
Animator: AI-Powered Hand‑Drawn Video Generator from Text Prompts
Animator creates narrated hand‑drawn animation videos from a simple text prompt in seconds, generating script, scenes, narration and icons via Python.