---
title: "SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.08196v1"
permalink: "https://feed.astralor.com/items/itm_fd9aa86a041d0b6b11a5c9c5"
published: "2026-11-05T15:51:39.000Z"
score: 55
channel: "tech"
tags: ["LLM","AI Agent","SMART","State-based Multi Agent","Reasoning Traces","Verification-oriented Problem-Solving Complex","Complex"]
---

# SMART: State-based Multi Agent Reasoning Traces for Verification-oriented Problem-Solving

## At a glance

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 th…

## Key points

- 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.

## Full text

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%.

---

Verify against the original before citing; curated by Astral Feed: https://feed.astralor.com/items/itm_fd9aa86a041d0b6b11a5c9c5