A Tree-Based Search Algorithm with Global Pheromone and Local Signal Guidance for Scientific Chart Reasoning

Min Zhou, Zhiheng Qi, Tianlin Zhu, Jan Vijg () and Xiaoshui Huang ()
Additional contact information
Min Zhou: School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China
Zhiheng Qi: School of Basic Medical Sciences and Forensic Medicine, Hangzhou Medical College, Hangzhou 310013, China
Tianlin Zhu: School of Computer Science and Artificial Intelligence, The Jiangxi University of Finance and Economics, Nanchang 330013, China
Jan Vijg: Department of Genetics, Albert Einstein College of Medicine, 1301 Morris Park Avenue, Bronx, NY 10461, USA
Xiaoshui Huang: School of Public Health, Shanghai Jiao Tong University School of Medicine, Shanghai 200080, China

Mathematics, 2025, vol. 13, issue 17, 1-18

Abstract: Chart reasoning, a critical task for automating data interpretation in domains such as aiding scientific data analysis and medical diagnostics, leverages large-scale vision language models (VLMs) to interpret chart images and answer natural language questions, enabling semantic understanding that enhances knowledge accessibility and supports data-driven decision making across diverse domains. In this work, we formalize chart reasoning as a sequential decision-making problem governed by a Markov Decision Process (MDP), thereby providing a mathematically grounded framework for analyzing visual question answering tasks. While recent advances such as multi-step reasoning with Monte Carlo tree search (MCTS) offer interpretable and stochastic planning capabilities, these methods often suffer from redundant path exploration and inefficient reward propagation. To address these challenges, we propose a novel algorithmic framework that integrates a pheromone-guided search strategy inspired by Ant Colony Optimization (ACO). In our approach, chart reasoning is cast as a combinatorial optimization problem over a dynamically evolving search tree, where path desirability is governed by pheromone concentration functions that capture global phenomena across search episodes and are reinforced through trajectory-level rewards. Transition probabilities are further modulated by local signals, which are evaluations derived from the immediate linguistic feedback of large language models. This enables fine grained decision making at each step while preserving long-term planning efficacy. Extensive experiments across four benchmark datasets, ChartQA, MathVista, GRAB, and ChartX, demonstrate the effectiveness of our approach, with multi-agent reasoning and pheromone guidance yielding success rate improvements of +18.4% and +7.6%, respectively.

Keywords: Markov decision processes; Monte Carlo methods; ant colony optimization; stochastic search algorithms (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2025
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/13/17/2739/pdf (application/pdf)
https://www.mdpi.com/2227-7390/13/17/2739/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:13:y:2025:i:17:p:2739-:d:1732574

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().