Prime Agent: A self-improving RLM agent
Prime Agent is our open-source, self-improving coding harness built around two abstractions: the Recursive Language Model (RLM) and the Continual Harness. With Opus 5, it achieves 95.5% on ARC-AGI-3, surpassing the reported human expert baseline.
Prime Agent: A self-improving RLM agent Today, we are launching Prime Agent, our self-improving coding harness designed around two abstractions, the Recursive Language Model (RLM) [citation] and Continual Harness [citation]. Modern harness designs were built around the capabilities of earlier generations of models, and they do not reflect what frontier models can do today: fixed tool-calling schemas and context compaction force the model to work around its own scaffolding instead of leveraging it. Static, hand-engineered sub-agents, prompts, skills, and memory are set once at design time…
saved by
related reading
- Prime Agent: A Self-Improving RLM Harnessarxiv.org
- PostTrainBenchposttrainbench.com
- Building Effective AI Agents \ Anthropicanthropic.com
- Harness Engineering for Self-Improvement | Lil'Loglilianweng.github.io
- LLM Powered Autonomous Agents | Lil'Loglilianweng.github.io
- SotA ARC-AGI-2 Results with REPL Agents | Symbolica Blogsymbolica.ai
- Composer2.pdfcursor.com
- Building Effective AI Agents \ Anthropicanthropic.com
- [2606.09498] Self-Harness: Harnesses That Improve Themselvesarxiv.org
- Building reliable AI agents · parth sareenparthsareen.com
- Effective harnesses for long-running agents \ Anthropicanthropic.com
- Arjun Virkarjunvirk.com