Adversarial Review: Structured Disagreement for Grounded Agentic Code Review
Early multi-agent LLM systems often used role-separated teams, yet scaling agent count yields diminishing returns on repository-level coding tasks. Recent alternatives treat agents as passive tools (subagents), yet this removes the benefits of agent interaction entirely. We study whether a subagent paradigm can support...
Eric S. Qiu, J. Gill
· 0 citations