Very interesting paper on recursive self-improvement. The whole stack is released. Machine learning engineering gives recursive self-improve…

Very interesting paper on recursive self-improvement. The whole stack is released. Machine learning engineering gives recursive self-improvement a concrete, executable testbed. OpenMLE is an open full-stack system for that research, spanning verifiable task environments with execution feedback, operator learning, and long-horizon search. On top of it the team post-trains Frontis-MA1, a 35B meta-evolution agent aligned around four atomic program-evolution operators. Draft, Improve, Debug, Crossover. The same four operators are trained through execution-grounded SFT and RL, then composed into long-horizon search, so learning and evolution run in one loop. On MLE-Bench Lite under a 12-hour per-task budget on a single RTX 4090 capped at 12 GB VRAM, Medal Average climbs from 39.39% to 60.61% over the base model, reaching 71.21% with asynchronous search and benchmark-independent experience priors. That exceeds GPT-5.5 with Codex and approaches GPT-5.6 Sol and the 2.8T Kimi K3. With the framework fixed, swapping in the trained model raises Match-SOTA from 50% to 70%. With the model fixed, swapping in the search framework raises it from 20% to 50%. Paper: https://arxiv.org/abs/2607.28568 Learn to build effective AI agents in our academy: https://academy.dair.ai/

Source: DAIR.AI (X) | 2026-07-31