Chapter 2 · 2025
Optimizing Sequential Multi-Step Tasks with Parallel LLM Agents
Enhao Zhang, Erkang Zhu, Gagan Bansal
Abstract
LLM-based multi-agent systems often incur high latency for complex tasks requiring multiple iterative reasoning cycles. This paper proposes M1-Parallel, a framework that concurrently runs multiple multi-agent teams to uncover distinct solution paths. By leveraging an event-driven communication model, M1-Parallel efficiently capitalizes on the inherent diversity of valid plans to reduce latency or boost task completion rates, demonstrating significant speedup and higher completion rates on complex tasks.
Topics
LLM agentsmulti-agent systemsmulti-step tasksparallel executiontask optimization
Relevance Scores
Long-Horizon Score85
Enterprise Score80
Completeness75
Paper Info
Year2025
Venue
Type
ChapterCh. 2
Authors3
Zone III Analysis
Related Papers
Tree of Thoughts: Deliberate Problem Solving with Large…
2023 · Ch.1
HuggingGPT: Solving AI Tasks with ChatGPT and its Frien…
2023 · Ch.4
Generative Agents: Interactive Simulacra of Human Behav…
2023 · Ch.2
MemGPT: Towards LLMs as Operating Systems
2023 · Ch.2
View all Chapter 2 papers →