Why 'Recursive Language Models': a harness invoking harnesses is itself a model
a1zhang · x · 2026-11-20
Alex Zhang explains the origin of the RLM name: experiments show that harnesses recursively invoking harnesses exhibit the same locally in-distribution property, with the harness now abstracted as a sub-LLM — the harness is treated as a model.
He argues we shouldn't think of harnesses only as complex scaffolds like SWE-Agent or Claude Code; even a language model that merely invokes swarms of language models is a harness. Many ideas in the paper motivated the RLM, and he suspects many other equally or more useful harness designs remain to be found.
Related event: MIT Paper: LM Harnesses Are Compositional Generalizers, Not Crutches(10 posts)→
More from coding & agent
- DeepMind's Antigravity Robotics Plugin: 2 Prompts, ~20 Minutes to Command a Real FR3 Duo Arm — jackyliang42 · 2026-11-21
- Security & Web3 Firewall MCP Server Hits Official Registry: Detects Tool-Poisoning and Rug-Pull Drift — ezelech · 2026-11-21
- Artificial Analysis Launches Search API Benchmark Covering 26 Products Across 14 Providers — ArtificialAnlys · 2026-11-21
- Pydantic hacks Mypy detection: why type checkers crawl and how to fake your way to speed — charliermarsh · 2026-11-21
- MAI Code 2 hands-on: replacing Claude as orchestrator, tops Terminal-Bench — imdigitalashish · 2026-11-21
- LangGraph Agent on WhatsApp: Voice, Photos, Memory — an Open-Source Starter With Solid Design Notes — Nice-Brilliant1697 · 2026-11-21