Tag
Prime Intellect launches Prime Agent, a fully open-source self-improving coding harness built around Recursive Language Model (RLM) and Continual Harness abstractions, enabling persistent sub-agents and dynamic tooling via a REPL-based interface.
This blog post argues that better generalization in language models should come from the 'harness' — the interface program — rather than just scaling training data. Experiments show that a Recursive Language Model harness enables length and domain generalization far beyond what the base Transformer achieves.
LangChain announces support for recursive language model (RLM) workflows in Deep Agents, with a 6-minute explainer video.
MIT open-sourced the RLM (Recursive Language Models) inference library, which handles ultra-long contexts by having the model recursively call itself programmatically, solving the limited context window problem of traditional models.
This update to the RLM arXiv paper adds depth>1 experiments with recursive RLM calls, showing significant performance gains on OOLONG-Pairs and other benchmarks, along with new comparisons to OpenCode and Claude Code, additional training results on MRCRv2, and an expanded error analysis.