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
- agents-best-practices: a provider-neutral Agent Skill for designing and auditing agentic harnesses — tom_doerr · 2026-09-11
- Cognition's SWE-2 uses a KKT duality argument in RL to shift the effort Pareto curve — YouJiacheng · 2026-09-11
- First-ever Three.js Conference lands in Paris, with a panel on AI-shortened design workflows — OdinLovis · 2026-09-11
- Data engineering, not agent frameworks, is the real bottleneck for enterprise AI agents — dhruv2038 · 2026-09-11
- RTK Terminal Compression Cuts Tokens but Leaves Your AI Coding Bill Unchanged — Bartaseth · 2026-09-11
- GPT-6 Astra beats Factorio with enemies in 44 in-game hours at ~$4,500 API cost — liminal_bardo · 2026-09-11