Score: 0

Can Small Agent Collaboration Beat a Single Big LLM?

Published: January 16, 2026 | arXiv ID: 2601.11327v1

By: Agata Żywot, Xinyi Chen, Maarten de Rijke

Potential Business Impact:

Small AI with tools beats big AI without.

Business Areas:
Intelligent Systems Artificial Intelligence, Data and Analytics, Science and Engineering

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.

Country of Origin
🇳🇱 Netherlands

Page Count
10 pages

Category
Computer Science:
Multiagent Systems