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

**Authors:** Sai Vallurupalli, Francis Ferraro  
**Lab:** University of Maryland, Baltimore County · **Published:** 5 Nov 2026  
**Links:** [arXiv](https://arxiv.org/abs/2611.08196) · [PDF](https://arxiv.org/pdf/2611.08196) · [This page](https://omen-bit.github.io/ai-paper-daily/paper/2611.08196.html)

## Key numbers

- **20%**: …guided solution reasoning improves validation performance up to 20% on complex scientific claims spanning 3 datasets.
- **5%**: We show that grounding premises in real-world knowledge is necessary and improves performance up to 5%

## 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%.

---

Notes written by AI from the paper, numbers copied from the abstract. Check the paper before you rely on them. From AI Papers Daily.