Today's edition highlights the expansion of recursive self-improvement into foundational territories, from frontier pre-training infrastructure to byte-level architectural conversions.
The loop: The system decomposes frontier pre-training into smaller loops that repair broken steps, which improves the data pipelines and infrastructure, making the resulting foundation model better.
A framework that applies recursive self-improvement to frontier pre-training by decomposing the unrepeatable run into smaller, verifiable loops that repair data pipelines and infrastructure.
The loop: A 27B subword model generates on-policy dialogue and behavioral supervision data, which is used to train its conversion into a pure byte-level model, making its successor capable of byte-level processing.
A 27B subword model is converted into a pure byte-level model without architectural patching by training it on supervised bytes generated entirely by the original model itself.
The loop: An LLM agent generates structured hypotheses from its experiences and tests them through a falsification-gated process, which improves its persistent memory, making the agent more successful and safer at future tasks.
A verifier-grounded framework that allows LLM agents to test experience-derived behavioral updates before committing them to persistent memory, ensuring only reusable and safe knowledge is retained.
The loop: Vexorium-Agent records its proof attempts and converts learned patterns into compiler-checked programmatic rewrite rules, which improves its own harness, making the agent more effective at solving future Lean proofs.
An agentic system for Lean proofs that achieves high performance by routing steps to cost-effective models and converting learned patterns into compiler-checked programmatic rewrite rules.
The loop: The InfraRSI agentic harness co-optimizes launch knobs and code patches for distributed training, which improves the training infrastructure, making the system more efficient at running its own optimization tasks.
An agentic harness that turns open-ended human commands into verified training optimizations by co-optimizing launch settings and code patches for distributed LLM training.
The loop: The BVSR framework applies evolutionary principles to the generation and selection of creative research ideas, which improves the AI scientists, making them better at autonomous scientific discovery.
An official implementation of a framework that improves creative idea generation in AI scientists through blind variation and selective retention.
The loop: A model analyzes the effects of poisoned fine-tuning data, which improves data filtering strategies, which makes future models more robust against data poisoning.
