让大模型先建模再推理，有效减少规划错误。
Model-First Reasoning LLM Agents: Reducing Hallucinations through Explicit Problem Modeling
- 先构建问题的显式模型，再生成解决方案
- 在多个任务中约束违规率显著降低
- 适合需要高可靠性的复杂规划场景
大型语言模型在复杂多步规划任务中常出现约束违反和解不一致的问题。现有方法如思维链（Chain-of-Thought）和ReAct依赖隐式状态追踪，缺乏显式问题表示。受经典AI规划启发，我们提出模型优先推理（Model-First Reasoning, MFR），一种两阶段范式：首先由大模型构建问题的显式模型，明确实体、状态变量、动作和约束，再生成求解计划。在医疗排班、路径规划、资源分配、逻辑谜题和过程合成等多个领域，MFR相比思维链和ReAct显著降低约束违规率并提升解的质量。消融实验表明，显式建模阶段对性能提升至关重要。结果表明，许多大模型规划失败源于表征缺陷而非推理能力不足，凸显显式建模在构建鲁棒、可解释智能体中的关键作用。所有提示、评估流程与任务数据集均已公开，确保可复现性。
原文摘要 · Abstract (English)
Large Language Models (LLMs) often struggle with complex multi-step planning tasks, showing high rates of constraint violations and inconsistent solutions. Existing strategies such as Chain-of-Thought and ReAct rely on implicit state tracking and lack an explicit problem representation. Inspired by classical AI planning, we propose Model-First Reasoning (MFR), a two-phase paradigm in which the LLM first constructs an explicit model of the problem, defining entities, state variables, actions, and constraints, before generating a solution plan. Across multiple planning domains, including medical scheduling, route planning, resource allocation, logic puzzles, and procedural synthesis, MFR reduces constraint violations and improves solution quality compared to Chain-of-Thought and ReAct. Ablation studies show that the explicit modeling phase is critical for these gains. Our results suggest that many LLM planning failures stem from representational deficiencies rather than reasoning limitations, highlighting explicit modeling as a key component for robust and interpretable AI agents. All prompts, evaluation procedures, and task datasets are documented to facilitate reproducibility.
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。