提出系统化分解复杂LLM任务的新方法，提升可靠性。
An approach for systematic decomposition of complex llm tasks
- 将任务建模为约束问题，用形式化复杂度度量指导拆解。
- 在SAT-Bench和Spider数据集上，分解后模型表现显著提升。
- 适合需要高可靠性的复杂任务，如自动推理与数据库查询。
大型语言模型在复杂任务上存在可靠性问题，现有分解方法多依赖启发式或人工设计。本文提出一种系统性分解框架——约束诱导复杂度分析（ACONIC），将任务建模为约束问题，并利用形式化复杂度度量指导分解过程。在组合类任务（SAT-Bench）和大模型数据库查询任务（Spider）上，按照复杂度度量进行分解后，智能体性能明显提升。
原文摘要 · Abstract (English)
Large Language Models (LLMs) suffer from reliability issues on complex tasks, as existing decomposition methods are heuristic and rely on agent or manual decomposition. This work introduces a novel, systematic decomposition framework that we call Analysis of CONstraint-Induced Complexity (ACONIC), which models the task as a constraint problem and leverages formal complexity measures to guide decomposition. On combinatorial (SAT-Bench) and LLM database querying tasks (Spider), we find that by decomposing the tasks following the measure of complexity, agent can perform considerably better.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。