AI RESEARCH
More Is Not Always Better: Cross-Component Interference in LLM Agent Scaffolding
arXiv CS.CL
•
ArXi:2605.05716v1 Announce Type: cross LLM agent systems are built by stacking scaffolding components (planning, tools, memory, self-reflection, retrieval) assuming is better. We study cross-component interference (CCI): degradation when components interact destructively. We run a full factorial experiment over all 2^5=32 subsets of five components on HotpotQA and GSM8K with Llama-3.1-8B/70B (96 conditions, up to 10 seeds