Cross-Component Interference Undermines LLM Agent Stacking

Researchers studying LLM agent scaffolding have found that stacking more components does not reliably improve performance, a phenomenon they term cross-component interference. In controlled experiments across 32 component subsets on HotpotQA and GSM8K using Llama-3.1-8B and 70B, a single-tool agent outperformed a fully equipped system by 32 percent on HotpotQA, while a three-component subset beat the all-inclusive configuration by 79 percent on GSM8K.