Can Small Agent Collaboration Beat a Single Big LLM?

Abstract: This report studies whether small, tool-augmented agents can match or outperform larger monolithic models on the GAIA benchmark. Using Qwen3 models (4B-32B) within an adapted Agentic-Reasoning framework, we isolate the effects of model scale, explicit thinking (no thinking, planner-only, or full), and tool use (search, code, mind-map). Tool augmentation provides the largest and most consistent gains. Using tools, 4B models can outperform 32B models without tool access on GAIA in our experimental setup. In contrast, explicit thinking is highly configuration- and difficulty-dependent: planner-only thinking can improve decomposition and constraint tracking, while unrestricted full thinking often degrades performance by destabilizing tool orchestration, leading to skipped verification steps, excessive tool calls, non-termination, and output-format drift.