> ## Documentation Index
> Fetch the complete documentation index at: https://docs.qredence.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# RLM runtime (`packages/coding-agent/src/core/rlm-runtime/`)

> Recursive language model (rlm(...)) spawns real child agents (SubagentRuntimeHost, RlmSubagentRuntime). Subagents run in parallel or background and return results programmatically. The RLM...

Recursive language model (`rlm(...)`) spawns real child agents (`SubagentRuntimeHost`, `RlmSubagentRuntime`). Subagents run in parallel or background and return results programmatically. The RLM harness (`/refine`) uses trajectory evidence to update supplemental state; it does not modify the base prompt.

Related: [Coding agent index](/fleet-prime-agent/packages--coding-agent), [Refinement](/fleet-prime-agent/packages--coding-agent--refinement)