Parallelism Meets Adaptiveness: Scalable Documents Understanding in Multi-Agent LLM Systems

TL;DR

This paper introduces a scalable, adaptive multi-agent LLM framework that enhances collaboration through dynamic task routing, feedback, and competition, leading to better factual coverage, coherence, and efficiency.

Contribution

It presents a novel coordination framework combining adaptiveness and structured competition, improving multi-agent LLM performance in complex tasks.

Findings

Improved factual coverage and coherence

Enhanced efficiency over static baselines

Effective use of structured competition

Abstract

Large language model (LLM) agents have shown increasing promise for collaborative task completion. However, existing multi-agent frameworks often rely on static workflows, fixed roles, and limited inter-agent communication, reducing their effectiveness in open-ended, high-complexity domains. This paper proposes a coordination framework that enables adaptiveness through three core mechanisms: dynamic task routing, bidirectional feedback, and parallel agent evaluation. The framework allows agents to reallocate tasks based on confidence and workload, exchange structured critiques to iteratively improve outputs, and crucially compete on high-ambiguity subtasks with evaluator-driven selection of the most suitable result. We instantiate these principles in a modular architecture and demonstrate substantial improvements in factual coverage, coherence, and efficiency over static and partially adaptive baselines. Our findings highlight the benefits of incorporating both adaptiveness and structured competition in multi-agent LLM systems.