Sttr fast-track: combinatorial reasoning

Award Recipient: Icosa Computing

Funding Agency: National Science Foundation (NSF)

Federal Grant Program: NSF Technology, Innovation, and Partnerships (CFDA 47.084)

Award Amount: $1.42M

Award Date: September 1, 2025

Performance Period: Through February 29, 2028

Location: New York, NY

This Small Business Technology Transfer (STTR) Fast-Track Cooperative Agreement funds the development of advanced artificial intelligence (AI) systems capable of sophisticated, transparent reasoning through integration of large language models with physics-inspired optimization methods. The project delivers a novel framework that samples multiple outputs from language models, embeds reasoning steps semantically, constructs cost functions based on frequencies and correlations, and leverages Ising machines—specialized physics-based optimizers—to select coherent reasoning chains. This technical approach addresses critical reliability challenges in AI systems used for high-stakes decision-making in finance, law, and healthcare by departing from purely neural or reward-driven paradigms.

The initiative advances U.S. competitiveness in AI through energy-efficient computing methods that mimic human-like reasoning while establishing empirical best practices for deploying Ising machines in AI reasoning pipelines. Broader impacts include fostering sustainable computing practices, supporting hardware and software advancements, creating employment opportunities, and enabling safer, more effective AI applications across government, sustainability, and commercial sectors. The work encompasses designing advanced cost functions and incorporating high-performance computing hardware optimization to establish a replicable model for intelligent reasoning systems.

Abstract

The broader/commercial impact of this small business technology transfer fast-track pilot project lies in advancing artificial intelligence (AI) systems to think in a sophisticated and transparent way, addressing the growing challenge of errors and unreliable outputs in language models used for complex decision-making. This effort tackles issues like inaccurate reasoning which can lead to costly mistakes in fields such as finance, law, and healthcare. Blending language models with novel efficient computing methods inspired by physics leads to smarter AI that mimics human-like reasoning while being energy-efficient. This project will contribute to boost U.S. Leadership in AI and will encourage further research in hardware, software and theory for optimization leading to economic competitiveness. Additional benefits include fostering sustainable computing practices and advancements in hardware and software that could create jobs and enhance AI applications in government, sustainability, and beyond, ultimately benefiting society with safer and more effective technology. This small business technology transfer fast-track pilot project advances a high-risk, high-reward innovation mapping abstract reasoning into discrete, optimizable structures?a departure from purely neural or reward-driven paradigms of AI. More particularly, the project will establish the setup and empirical best practices for leveraging ising machines, which are specialized physics-based optimizers running on high-performance computing hardware, in AI reasoning pipelines. The core technical innovation consists of a framework for sampling multiple outputs from large language models, embedding reasoning steps semantically, constructing a cost function based on frequencies and correlations, and optimizing IT to select coherent reasoning chains for final AI responses. The scope encompasses designing an advanced cost function in the initial phase, incorporating higher-order correlations inspired by physics principles, and tuning accelerated ising solvers in the subsequent phase to achieve reliable performance on reasoning benchmarks. Performance will be evaluated using metrics on diverse datasets, including confidence intervals, aiming for improvements over baselines while ensuring energy efficiency and explainability, with real-world testing in retrieval-augmented scenarios to validate commercial viability. This project will enhance AI accuracy and reduce hallucinations without the need of extensive pre-training and will result in a modular reasoning engine compatible with both proprietary and open-source large-language models. This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the foundation's intellectual merit and broader impacts review criteria.- subawards are planned for this award.