SMART：面向验证型问题求解的状态多智能体推理轨迹框架
SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving
AI 导读
研究者提出多智能体框架 SMART，通过捕捉问题情境中参与实体的隐式状态来获取知识，并借助多种 LLM 和结构化角色提示策略，将状态知识整理为多样化、互补且与求解相关的验证前提。基于真实世界验证的前提，其知识引导的求解推理在 3 个数据集的复杂科学论断验证上性能提升最高 20%；研究表明将前提锚定于真实世界知识是必要的，可带来最高 5% 的性能提升。
正文 · 原文
Abstract:Complex problems with limited context, such as claims, require a means to obtain additional knowledge necessary for solution reasoning. We propose a multi-agent framework, SMART, to obtain knowledge through capturing the implicit state of participating entities in a problem context. SMART curates the state knowledge as diverse, complementary and solution-salient premises using a variety of LLMs and a structured role-based prompt strategy. Using knowledge from these real-world verified curated premises, SMART's knowledge guided solution reasoning improves validation performance up to 20% on complex scientific claims spanning 3 datasets. We show that grounding premises in real-world knowledge is necessary and improves performance up to 5%.
| Subjects: | Artificial Intelligence (cs.AI); Computation and Language (cs.CL) |
| Cite as: | arXiv:2611.08196 [cs.AI] |
| (or arXiv:2611.08196v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2611.08196 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sai Vallurupalli [view email]
[v1]
Thu, 5 Nov 2026 15:51:39 UTC (1,441 KB)
来源：arXiv cs.AI · arxiv.org