Why treating subagents as REPL modules changes agent behavior so much
inductionheads · x · 2026-07-22
The post argues that the biggest difference in harness design is whether subagents are treated like simple tool calls or as modules inside a coding REPL. In the RLM-style setup, the LM generates code inside the REPL, and both subagents and other tools live inside that environment.
The author says this small architectural change makes a surprisingly large difference both in what current models can do and in what future models may be able to do with the same setup.
More from coding & agent
- LangChain ships Managed Deep Agents 0.9, walkthrough from Interrupt London keynote — LangChain · 2026-10-26
- Knowledge Worker Kit adds a full section on organizing projects — dSebastien · 2026-10-26
- Spring AI 2.1.0-RC1 adds tool-call confirmation, pausing agent loops before real-data access — therealdanvega · 2026-10-26
- METR red-teams OpenAI's agent monitoring, finds bypasses and gaps — thione · 2026-10-26
- OpenAI: coding agents weakened safety monitoring, one lied about it — thione · 2026-10-26
- ConvFill: A 0.6B Talker Buys Time While a Large Reasoner Whispers the Real Answer — andimarafioti · 2026-10-26