Research Experience

Agentic Site Reliability Engineering: AI for SRE

2026 | Research Intern, advised by Prof. Tianyin Xu (UIUC)

🔬 Contributing to SREGym — Benchmark for AI SRE Agents

• Contributing to SREGym, an open-source benchmark for evaluating AI agents on realistic cloud-native system failures, through case studies and postmortem analysis of real-world outages projected into reproducible benchmark problems.
• Studied agent failure modes documented in the SREGym and Stratus papers (cross-layer reasoning gaps, greedy diagnosis anchoring, reward hacking).
• Designing fault scenarios and evaluation oracles that target these weaknesses and quantify where state-of-the-art SRE agents fail to reason across system layers, from control-plane admission to network policy.

Code Generation in Bangla: Low-Resource Language Adaptation

2025 | Shared Task at the BLP Workshop, co-located with IJCNLP-AACL

🏆 4th Place out of 32 Teams — 85% Accuracy

• Investigated code generation in Bangla by fine-tuning open-source models (Llama 3, TigerLLM, Qwen) using parameter-efficient LoRA adapters to overcome data scarcity.
• Enhanced reasoning via Chain-of-Thought (CoT) prompting and a self-refinement loop that iteratively critiques and corrects generated code based on execution feedback.
• Conducted rigorous error analysis to identify failure modes in code generation tasks.
• Publication: AdversaryAI at BLP-2025 Task 2: A Think, Refine, and Generate (TriGen) System with LoRA and Self-Refinement for Code Generation

BRAINTEASER: Advanced Commonsense Reasoning in Language Models

2024 | Shared Task at SemEval 2024, co-located with NAACL

• Designed data augmentation pipelines to improve model robustness for complex commonsense reasoning tasks involving lateral thinking puzzles.
• Conducted a comparative analysis of advanced language models, analyzing performance gaps and reasoning patterns in non-standard logical scenarios.
• Publication: Deja Vu at SemEval 2024 Task 9: A Comparative Study of Advanced Language Models for Commonsense Reasoning

Violence Inciting Text Detection (VITD) in Bangla

2023 | Shared Task at the BLP Workshop, co-located with EMNLP

📊 Top 20 — Improved from Rank 19 → 12 in Post-evaluation

• Applied semi-supervised self-training to address class imbalance, significantly improving performance on minority classes.
• Enhanced dataset diversity through back-translation using the Googletrans API, improving semantic variety while correcting linguistic inconsistencies.
• Implemented an ensemble approach combining multiple transformer models with bagging and majority voting to reduce prediction variance.
• Publication: Team_Syrax at BLP-2023 Task 1: Data Augmentation and Ensemble Based Approach for Violence Inciting Text Detection in Bangla

Improving Answer Space Diversity in Visual Question Answering (VQA)

2022 | Undergraduate Thesis Project

• Conducted a comparative study of VQA methods, identifying core limitations in answer distribution.
• Addressed the “Answer Space Diversity” limitation by augmenting training data with automatically generated, contextually relevant QA pairs using template-based synthesis.
• Demonstrated improved performance on long-tail answer categories, reducing model bias toward frequent answers.