MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework
Designing effective algorithmic components remains a fundamental obstacle in tackling NP hard combinatorial optimization problems (COPs), where solvers often rely on carefully hand-crafted strategies. Despite recent advances in using large language models (LLMs) to synthesize high-quality components, most approaches restrict the search to a single element - commonly a heuristic scoring function - thus missing broader opportunities for innovation. In this paper, we introduce a broader formulation of solver design as a multi-strategy optimization problem, which seeks to jointly improve a set of interdependent components under a unified objective. To address this, we propose Multi-strategy Optimization via Turn-based Interactive Framework (MOTIF)—a novel framework based on Monte Carlo Tree Search that facilitates turn-based optimization between two LLM agents. At each turn, an agent improves one component by leveraging the history of both its own and its opponent’s prior updates, promoting both competitive pressure and emergent cooperation. This structured interaction broadens the search landscape and encourages the discovery of diverse, high-performing solutions. Experiments across multiple COP domains show that MOTIF consistently outperforms state-of-the-art methods, highlighting the promise of turn-based, multi-agent prompting for fully automated solver design.
Date and Time
Location
Hosts
Registration
Add Event to Calendar
Speakers
Prof Huynh of School of Information and Communication Technology (SoICT), Hanoi University of Science and Technology (HUST)
MOTIF: Multi-strategy Optimization via Turn-based Interactive Framework
Designing effective algorithmic components remains a fundamental obstacle in tackling NP hard combinatorial optimization problems (COPs), where solvers often rely on carefully hand-crafted strategies. Despite recent advances in using large language models (LLMs) to synthesize high-quality components, most approaches restrict the search to a single element - commonly a heuristic scoring function - thus missing broader opportunities for innovation. In this paper, we introduce a broader formulation of solver design as a multi-strategy optimization problem, which seeks to jointly improve a set of interdependent components under a unified objective. To address this, we propose Multi-strategy Optimization via Turn-based Interactive Framework (MOTIF)—a novel framework based on Monte Carlo Tree Search that facilitates turn-based optimization between two LLM agents. At each turn, an agent improves one component by leveraging the history of both its own and its opponent’s prior updates, promoting both competitive pressure and emergent cooperation. This structured interaction broadens the search landscape and encourages the discovery of diverse, high-performing solutions. Experiments across multiple COP domains show that MOTIF consistently outperforms state-of-the-art methods, highlighting the promise of turn-based, multi-agent prompting for fully automated solver design.
Biography:
Huynh Thi Thanh Binh is Professor and Vice Dean of the School of Information and Communication Technology (SoICT), Hanoi University of Science and Technology (HUST).
She is Head of Optimization Group. She is Chair (2025-2027)/ Vice Chair (2023-2024) of the Science Committee on Computer Science and Information Technology, The National Foundation for Science and Technology Development – NAFOSTED. Her current research interests: Artificial Intelligence, Algorithms and Optimization, Computational Intelligence, Memetic Computing, Evolutionary Multitasking.
She has published more than 150 refereed academic papers/articles. She is Associate Editor of the Swarm and Evolutionary Computation (2024 – now), Engineering Applications of Artificial Intelligence Journal (2021-now), IEEE Transactions on Emerging Topics in Computational Intelligence (2022-now).
She is Chair of IEEE Vietnam section, Chair of Collaboration and Engagement Committee of IEEE Asia Pacific.