aiqbench takeAI Products

Prime Intellect has open-sourced Prime Agent, an autonomous coding harness that leverages Recursive Language Models (RLM) to treat sub-agent delegation as function calls within a persistent Python REPL. This architecture allows agents to dynamically edit their own prompts and memory mid-run while achieving performance metrics on ARC-AGI-3 that exceed reported human expert baselines using Opus 5. The release offers significant implications for AI research labs and engineering teams seeking scalable, self-improving agent frameworks capable of handling long-horizon tasks without fixed tool schemas.

Source coveringMarkTechPost

What this isA model's reading of the article and related coverage, written for aiqbench. Not the publisher's words.

Prime Intellect Releases Prime Agent: An Open-Source RLM Harness Where Sub-Agents Are Function Calls Inside Persistent IPython Kernel

MarkTechPostAugust 6, 20264 min read

Prime Intellect has open-sourced Prime Agent, a coding and research harness built on two abstractions: the Recursive Language Model, which turns sub-agent calls into functions inside a persistent IPython kernel, and the Continual Harness, which lets the agent edit its own prompts, skills, memory, and sub-agent specs mid-run. With Opus 5 it reports 95.5% RHAE Best@1 on ARC-AGI-3, above the reported human expert baseline of 95.4%. The post Prime Intellect Releases Prime Agent: An Open-Source RLM Harness Where Sub-Agents Are Function Calls Inside Persistent IPython Kernel appeared first on MarkTechPost.

Prime Intellect has open-sourced Prime Agent, a self-improving coding harness designed around two abstractions: the Recursive Language Model (RLM) and Continual Harness. Fixed tool schemas and context compaction force a model to work around its own scaffolding. Prime Agent replaces both with a persistent Python REPL and a rewritable harness. With Opus 5, it reports 95.5% on ARC-AGI-3, above the reported human expert baseline of 95.4%. It is MIT-licensed. Yes, today. Prime Agent installs on Linux or macOS with…

Excerpt shown under the publisher's RSS terms · 79 words · full text and figures are on the publisher's site

Read at MarkTechPost ↗Ask about this article