RRRoussel Rahman

Roussel Rahman

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Roussel Rahman has a total of 12 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Lost in space: uncovering fundamental limits of large language models in complex, spatial problem solving

    by Roussel Rahman, Catherine Sibert

    As agents based on Large Language Models (LLMs) are rapidly becoming assistive tools in the real world, it is important to understand the limits of their ability to reason and navigate in complex physical spaces. While LLMs have demonstrated impressive performance on many reasoning tasks, their spatial reasoning remains underexplored. We evaluated agents powered by five state-of-the-art open-source models on two complex spatial problems that humans excel at: the Tower of Hanoi (ToH) puzzle and the Tetris game. In contrast to humans, who are able to learn these tasks with ease and are able to interact with the environment with very little training, we find that the LLMs are badly lost in space. In the ToH task, the agents started well at low complexity levels but failed to find general, complexity-independent solution strategies that humans discover with little practice, culminating in performance collapse as task complexity increases. In Tetris, the models rarely produced legal placements, even in drastically simplified variants of the game. In both tasks, evaluating their paths in space relative to optimal or acceptable ones reflects a fundamental lack of understanding of physical space and its laws. Both tasks are fully describable in text, giving LLMs the best conditions to succeed; however, the agents still failed to follow the rules of the problems, diverged toward impossible paths, struggled to maintain objects and problem states, and did not demonstrate any understanding of gravity, rigid bodies, and solid boundaries. Altogether, these results highlight key differences between human and LLM problem-solving approaches and suggest an uphill battle in scaling purely language-based architectures into general problem solvers.

  • Open Access

    Bridging Human and Artificial Intelligence: Modeling Human Learning with Explainable AI Tools

    by Roussel Rahman, Jane Shtalenkova, Aashwin Ananda Mishra, Wan-Lin Hu

    We address a gap in Machine Learning–human alignment research by proposing that methods from Explainable AI (XAI) can be repurposed to quantitatively model human learning. To achieve alignment between human experts and Machine Learning (ML) models, we must first be able to explain the problem-solving strategies of human experts with the same rigor we apply to ML models. To demonstrate this approach, we model expertise in the complex domain of particle accelerator operations. Analyzing 14 years of operational text logs, we construct weighted graphs where nodes represent operational subtasks and edges capture their strategic relationships. We then examine these strategic models across four granularity levels. Our analysis reveals statistically significant changes with expertise at three of four graph levels. Remarkably, despite numerous possible ways to partition subtasks, operators across all expertise levels demonstrate a striking consistency in high-level strategy, partitioning the task into the same three functional communities. This suggests a shared “divide and conquer” cognitive framework. Expertise develops within this stable framework, as experts exhibit greater cognitive flexibility (forming more cross-community connections) and build more refined internal models. The primary contribution of this work is a methodology for creating a quantitative, interpretable baseline of expert human performance. This provides a “ground truth” for future research in alignment between humans and ML models, enabling a new approach to verification: the ML model’s representation of the task can be quantitatively compared against the human expert benchmark to measure their alignment. This paves the way for building safer, more interpretable partnerships between humans and ML models.

  • Open Access

    A Fragile Number Sense: Probing the Elemental Limits of Numerical Reasoning in LLMs

    by Roussel Rahman, Aashwin Ananda Mishra

    Large Language Models (LLMs) have demonstrated remarkable emergent capabilities, yet the robustness of their numerical reasoning remains an open question. While standard benchmarks evaluate LLM reasoning on complex problem sets using aggregated metrics, they often obscure foundational weaknesses. In this work, we probe LLM mathematical numeracy by evaluating performance on problems of escalating complexity, from constituent operations to combinatorial puzzles. We test several state-of-the-art LLM-based agents on a 100-problem challenge comprising four categories: (1) basic arithmetic, (2) advanced operations, (3) primality checking, and (4) the Game of 24 number puzzle. Our results show that while the agents achieved high accuracy on the first three categories, which require deterministic algorithmic execution, they consistently failed at the number puzzle, underlining its demand for a heuristic search over a large combinatorial space to be a significant bottleneck. These findings reveal that the agents' proficiency is largely confined to recalling and executing known algorithms, rather than performing generative problem-solving. This suggests their apparent numerical reasoning is more akin to sophisticated pattern-matching than flexible, analytical thought, limiting their potential for tasks that require novel or creative numerical insights.

  • Open Access

    Network Models of Expertise in the Complex Task of Operating Particle Accelerators

    by Roussel Rahman, Jane Shtalenkova, Aashwin Ananda Mishra, Wan-Lin Hu

    We implement a network-based approach to study expertise in a complex real-world task: operating particle accelerators. Most real-world tasks we learn and perform (e.g., driving cars, operating complex machines, solving mathematical problems) are difficult to learn because they are complex, and the best strategies are difficult to find from many possibilities. However, how we learn such complex tasks remains a partially solved mystery, as we cannot explain how the strategies evolve with practice due to the difficulties of collecting and modeling complex behavioral data. As complex tasks are generally networks of many elementary subtasks, we model task performance as networks or graphs of subtasks and investigate how the networks change with expertise. We develop the networks by processing the text in a large archive of operator logs from 14 years of operations using natural language processing and machine learning. The network changes are examined using a set of measures at four levels of granularity - individual subtasks, interconnections among subtasks, groups of subtasks, and the whole complex task. We find that the operators consistently change with expertise at the subtask, the interconnection, and the whole-task levels, but they show remarkable similarity in how subtasks are grouped. These results indicate that the operators of all stages of expertise adopt a common divide-and-conquer approach by breaking the complex task into parts of manageable complexity, but they differ in the frequency and structure of nested subtasks. Operational logs are common data sources from real-world settings where people collaborate with hardware and software environments to execute complex tasks, and the network models investigated in this study can be expanded to accommodate multi-modal data. Therefore, our network-based approach provides a practical way to investigate expertise in the real world.

  • SpotLight on Dynamics of Individual Learning

    by Roussel Rahman, Wayne D. Gray

    Averaging performance over a group of individuals implicitly assumes that there is only one set of methods for accomplishing the task and that all learners acquire those methods in the same sequence. We maintain that the average subject is a mythical beast and, rather than profiling a mythical beast, we ask “how do different people each learn the same complex task?” To answer our question, we use SpotLight—a tool for analyzing changes in individual performance as skill is acquired. Specifically, in this report, we use the SpotLight on 40 scores and measures of performance (some collected at millisecond level, others collected once per game), to investigate the skill acquisition of nine individuals each of whom devoted 31 h to becoming skilled players of the classic cognitive psychology game of Space Fortress (Mané & Donchin, 1989). Turning the SpotLight on our best and worst players reveals patterns of performance plateaus, dips, and leaps. Examining these patterns reveals differences as well as commonalities in the evolution of methods discovered and used by each individual across 31 hours of skill acquisition.


  • Vibration energy harvesting in a small channel fluid flow using piezoelectric transducer

    by Mehedi Hassan, Yeam Hossain, Rakib Mazumder, Roussel Rahman, Ashiqur Rahman

    This work is aimed at developing a way to harvest energy from a fluid stream with the application of piezoelectric transducers in a small channel. In this COMSOL Multiphysics based simulation study, it is attempted to harvest energy from the abundant renewable source of energy available in the form of kinetic energy of naturally occurring flow of fluids. The strategy involves harnessing energy from a fluid-actuator through generation of couples, eddies and vortices, resulting from the stagnation and separation of flow around a semi-circular bluff-body attached to a cantilever beam containing a piezoceramic layer. Fluctuation of fluidic pressure impulse on the beam due to vortex shedding and varying lift forces causes the flexible cantilever beam to oscillate in the direction normal to the fluid flow in a periodic manner. The periodic application and release of a mechanical strain upon the beam effected a generation of electric potential within the piezoelectric layer, thus enabling extraction of electrical energy from the kinetic energy of the fluid. The piezoelectric material properties and transducer design are kept unchanged throughout the study, whereas the configuration is tested with different fluids and varying flow characteristics. The size and geometry of the obstructing entity are systematically varied to closely inspect the output from different iterations and for finding the optimum design parameters. The intermittent changes in the generated forces and subsequent variation in the strain on the beam are also monitored to find definitive relationship with the electrical energy output.