Selected work

Representative Papers

RM -RF: Reward Model for Run-Free Unit Test Evaluation

Jan 19, 2026

This work proposes the first lightweight reward model capable of predicting multidimensional test quality—including executability, code coverage, and mutation kill rate—without executing tests, thereby circumventing the high latency and resource overhead inherent in traditional unit test evaluation that relies on repeated compilation and execution. Leveraging a multilingual dataset constructed from Java, Python, and Go, the model is trained using parameter-efficient strategies such as zero-shot inference, full fine-tuning, and LoRA. It achieves an average F1 score of 0.69 across all three quality metrics. By eliminating the need for actual test runs, this approach substantially reduces evaluation cost and latency, offering an efficient foundation for large-scale test generation and reinforcement learning–based test optimization.

1 citationsRead paper

Minimum distances of LDPC codes in 5G standard

Jul 06, 2026

This study addresses the minimum distance—a critical error-correction performance metric—of quasi-cyclic LDPC codes specified in the 5G NR standard, focusing on both high- and low-rate base graph 1 (BG1) configurations. By integrating algebraic analysis, combinatorial bounding algorithms, and cyclic modulo reduction techniques, the work establishes tight upper and lower bounds on the minimum distance for specific code instances: [9984, 8448] codes exhibit a minimum distance between 8 and 14, while [25344, 8448] codes range from 22 to 57. Furthermore, the paper introduces a novel early-termination strategy based on cyclic modulo reduction, which substantially reduces the computational complexity of parity-check operations during decoding. This approach enhances decoding efficiency without compromising error-correction performance.

0 citationsRead paper

Partial Automation of Verification Condition Proving for Reflex Programs (Draft)

Jun 22, 2026

This work addresses the challenge of formal verification for Reflex programs in industrial-scale control systems, where the generation of an excessive number of verification conditions often renders manual analysis impractical. To overcome this limitation, the authors propose a hybrid verification strategy that integrates a structured requirement annotation language with automated invariant inference based on program structure, coupled with an SMT solver to automatically discharge a substantial subset of verification conditions. By leveraging this synergistic approach, the method significantly reduces the number of verification tasks requiring human intervention, thereby enhancing the automation, feasibility, and overall efficiency of formal verification for large-scale process control systems.

0 citationsRead paper

RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation

May 06, 2026

We present our winning system for Task~B (generation with reference passages) in SemEval-2026 Task~8: MTRAGEval. Our method is a heterogeneous ensemble of seven LLMs with two prompting variants, where a GPT-4o-mini judge selects the best candidate per instance. We ranked 1st out of 26 teams, achieving a conditioned harmonic mean of 0.7827 and outperforming the strongest baseline (gpt-oss-120b, 0.6390). Ablations show that diversity in model families, scales, and prompting strategies is essential, with the ensemble consistently beating any single model. We also introduce Meno-Lite-0.1, a 7B domain-adapted model with a strong cost--performance trade-off, and analyse MTRAGEval, highlighting annotation limitations and directions for improvement. Our code is publicly available: https://github.com/RaguTeam/ragu_mtrag_semeval

0 citationsRead paper

Interpretable experiential learning based on state history and global feedback

May 01, 2026

This work addresses the challenge of explainable reinforcement learning in resource-constrained environments by proposing an experience-based learning model grounded in state-transition graphs. The model explicitly constructs a graph encoding both utility values and evidence counts, integrating a global feedback mechanism to enable transparent policy modeling and interpretable decision-making. By embedding explainability directly into the learning process, the approach maintains low computational overhead while achieving performance on the OpenAI Gym Atari Breakout benchmark comparable to that of certain neural network–based methods, thereby demonstrating its effectiveness and practicality in settings with limited computational resources.

0 citationsRead paper

Recent publications

Latest Papers

Minimum distances of LDPC codes in 5G standard

Jul 06, 2026

This study addresses the minimum distance—a critical error-correction performance metric—of quasi-cyclic LDPC codes specified in the 5G NR standard, focusing on both high- and low-rate base graph 1 (BG1) configurations. By integrating algebraic analysis, combinatorial bounding algorithms, and cyclic modulo reduction techniques, the work establishes tight upper and lower bounds on the minimum distance for specific code instances: [9984, 8448] codes exhibit a minimum distance between 8 and 14, while [25344, 8448] codes range from 22 to 57. Furthermore, the paper introduces a novel early-termination strategy based on cyclic modulo reduction, which substantially reduces the computational complexity of parity-check operations during decoding. This approach enhances decoding efficiency without compromising error-correction performance.

0 citationsRead paper

Partial Automation of Verification Condition Proving for Reflex Programs (Draft)

Jun 22, 2026

This work addresses the challenge of formal verification for Reflex programs in industrial-scale control systems, where the generation of an excessive number of verification conditions often renders manual analysis impractical. To overcome this limitation, the authors propose a hybrid verification strategy that integrates a structured requirement annotation language with automated invariant inference based on program structure, coupled with an SMT solver to automatically discharge a substantial subset of verification conditions. By leveraging this synergistic approach, the method significantly reduces the number of verification tasks requiring human intervention, thereby enhancing the automation, feasibility, and overall efficiency of formal verification for large-scale process control systems.

0 citationsRead paper

RaguTeam at SemEval-2026 Task 8: Meno and Friends in a Judge-Orchestrated LLM Ensemble for Faithful Multi-Turn Response Generation

May 06, 2026

We present our winning system for Task~B (generation with reference passages) in SemEval-2026 Task~8: MTRAGEval. Our method is a heterogeneous ensemble of seven LLMs with two prompting variants, where a GPT-4o-mini judge selects the best candidate per instance. We ranked 1st out of 26 teams, achieving a conditioned harmonic mean of 0.7827 and outperforming the strongest baseline (gpt-oss-120b, 0.6390). Ablations show that diversity in model families, scales, and prompting strategies is essential, with the ensemble consistently beating any single model. We also introduce Meno-Lite-0.1, a 7B domain-adapted model with a strong cost--performance trade-off, and analyse MTRAGEval, highlighting annotation limitations and directions for improvement. Our code is publicly available: https://github.com/RaguTeam/ragu_mtrag_semeval

0 citationsRead paper

Interpretable experiential learning based on state history and global feedback

May 01, 2026

This work addresses the challenge of explainable reinforcement learning in resource-constrained environments by proposing an experience-based learning model grounded in state-transition graphs. The model explicitly constructs a graph encoding both utility values and evidence counts, integrating a global feedback mechanism to enable transparent policy modeling and interpretable decision-making. By embedding explainability directly into the learning process, the approach maintains low computational overhead while achieving performance on the OpenAI Gym Atari Breakout benchmark comparable to that of certain neural network–based methods, thereby demonstrating its effectiveness and practicality in settings with limited computational resources.

0 citationsRead paper

Component-Adaptive and Lesion-Level Supervision for Improved Small Structure Segmentation in Brain MRI

Apr 09, 2026

This work addresses the challenge of segmenting small lesions in brain MRI, which is hindered by their minuscule scale and extreme class imbalance, often resulting in low recall and high false-negative rates with conventional methods. To overcome this, the authors propose a unified objective function, CATMIL, integrated within the nnU-Net framework, which jointly leverages voxel-level, connected-component-level, and lesion-level supervision. The approach innovatively combines adaptive weighting of connected components with multiple instance learning (MIL), employing a Component-Adaptive Tversky loss to balance the influence of lesions across varying sizes and incorporating lesion-level detection constraints to co-optimize segmentation and detection performance. Evaluated on the MSLesSeg dataset, the method achieves a Dice score of 0.7834, significantly improves recall for small lesions, reduces false negatives, and yields the lowest false-positive volume among existing approaches.

0 citationsRead paper