flâneur

Prime Agent: A Self-Improving RLM Harness

arxiv.org · 5,908 words · saved by 1 readers

Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent workflows. A persistent IPython REPL follows the Recursive Language Model abstraction for programmatic context processing and test-time compute, while Continual Harness preserves histories, memories, skills, prompts, and subagent specifications across trajectories. Recursive subagents coordinate through direct agent-to-agent communication, and the Agents View lets humans inspect and manage daemon-backed sessions. Prime Agent standardizes execution, recovery, verification, and resource accounting while leaving strategy construction to the model. This low-friction, expressive membrane prevents harness failures from becoming model failures and pushes measurement toward the model’s true maximal underlying capability. Prime Agent raises ARC-AGI-3 RHAE Best@1

Alex L. Zhang Kevin Thomas Sebastian Müller Elie Bakouch Daniel Auras Mika Senghaas Fares Obeid Konstantin Dunas Johannes Hagemann Sami Jaghouar Affiliation: Princeton University Prime Intellect MIT Affiliation: Correspondence: seth@primeintellect.ai, altzhang@mit.edu First published: August 5, 2026 • Current version: August 24, 2026 Abstract Language models are sequential processors, but long-horizon agency requires external information and computation beyond model weights and active context. Prime Agent is an open-source harness for long-horizon evaluation and coding-agent…

saved by

related reading