Beyond Gemini-3-Pro: Revisiting LLM Routing and Aggregation at Scale

TL;DR

This paper introduces JiSi, a novel framework for LLM collaboration that improves routing and aggregation, surpassing Gemini-3-Pro performance at lower costs through collective intelligence.

Contribution

JiSi innovatively combines query-response mixed routing, support-set-based aggregator selection, and adaptive switch mechanisms to enhance LLM collaboration and performance.

Findings

JiSi outperforms Gemini-3-Pro on nine benchmarks.

JiSi achieves similar or better results with only 47% of the cost.

Open-source LLM collaboration can surpass proprietary models.

Abstract

Large Language Models (LLMs) have rapidly advanced, with Gemini-3-Pro setting a new performance milestone. In this work, we explore collective intelligence as an alternative to monolithic scaling, and demonstrate that open-source LLMs' collaboration can surpass Gemini-3-Pro. We first revisit LLM routing and aggregation at scale and identify three key bottlenecks: (1) current train-free routers are limited by a query-based paradigm focusing solely on textual similarity; (2) recent aggregation methods remain largely static, failing to select appropriate aggregators for different tasks;(3) the complementarity of routing and aggregation remains underutilized. To address these problems, we introduce JiSi, a novel framework designed to release the full potential of LLMs' collaboration through three innovations: (1) Query-Response Mixed Routing capturing both semantic information and problem difficulty; (2) Support-Set-based Aggregator Selection jointly evaluating the aggregation and domain capacity of aggregators; (3) Adaptive Routing-Aggregation Switch dynamically leveraging the advantages of routing and aggregation. Comprehensive experiments on nine benchmarks demonstrate that JiSi can surpass Gemini-3-Pro with only 47% costs by orchestrating ten open-source LLMs, while outperforming mainstream baselines. It suggests that collective intelligence represents a novel path towards Artificial General Intelligence (AGI).