Fraol Batole

New Orleans, Louisiana

Bio: I am a Ph.D. student in Computer Science at Tulane University, where I recently transitioned with my advisor Prof. Hridesh Rajan. Prior to joining Tulane, I completed my Master’s degree at Iowa State University (ISU) and undertook graduate-level coursework at the University of North Dakota (UND). My academic journey began at Addis Ababa Science and Technology University, where I earned my undergraduate degree in Software Engineering, graduating Magna cum laude.

I am fortunate to collaborate with Prof. Tien N. Nguyen, Prof. Danny Dig, and Prof. Foutse Khomh.

Research

My research addresses the engineering of trustworthy AI systems. As LLM-based agents take on substantive software engineering tasks, fluent output is not a sufficient measure of correctness. My work builds the mechanisms that make AI behavior verifiable, drawing on program analysis and runtime verification to provide explicit guarantees rather than relying on model confidence alone. Two complementary threads organize this work.

Trustworthy AI Agents

Agents whose reasoning is grounded in program analysis and whose actions are verified before they touch a codebase.

RefineAct ASE 2026

A runtime verification framework for checking an LLM agent's proposed actions before execution.
Read more →
LocalizeAgent ICSE 2025

An evidence-grounded agent for localizing design issues in Java programs using structured program facts and iterative reasoning.
Read more →

Reliable & Verifiable AI

Analyzing, verifying, and repairing the AI systems themselves, so their behavior can be trusted and maintained.

NeuralState IEEE TSE 2026

A typestate analysis for statically detecting deep-learning API misuses before model training or execution.
Read more →
IRepair ESEC/FSE 2025

A targeted repair method that localizes and edits faulty LLM behavior while limiting disruption to general model performance.
Read more →

Browse all publications →

news

Jun 18, 2026	Our paper “RefineAct: Automatic Runtime Verification of LLM Agent Actions” has been accepted at ASE 2026! 🎉 A lightweight, non-formal implementation lives at aligned — full code coming soon.
Apr 13, 2026	I have been awarded the Distinguished Reviewer Award (Junior PC) at the International Conference on Mining Software Repositories (MSR) 2026.
Oct 02, 2025	I have been selected to serve as a Junior PC member for MSR 2026.
Aug 24, 2025	I have been invited to serve as a reviewer for the DL4C Workshop at NeurIPS 2025.
Jun 05, 2025	Our paper “Together We Are Better: LLM, IDE and Semantic Embedding to Assist Move Method Refactoring” has been accepted at ICSME 2025! 🎉

selected publications

ICSE’25

An LLM-Based Agent-Oriented Approach for Automated Code Design Issue Localization

Fraol Batole, David OBrien, Tien N. Nguyen, and 2 more authors

In 2025 IEEE/ACM 45th International Conference on Software Engineering (ICSE), 2025

Bib PDF Code

@inproceedings{batole2025localizeAgent,
  title = {An LLM-Based Agent-Oriented Approach for Automated Code Design Issue Localization},
  author = {Batole, Fraol and OBrien, David and Nguyen, Tien N. and Dyer, Robert and Rajan, Hridesh},
  year = {2025},
  booktitle = {2025 IEEE/ACM 45th International Conference on Software Engineering (ICSE)},
  publisher = {ICSE},
  organization = {IEEE},
}

ASE’26

RefineAct: Automatic Runtime Verification of LLM Agent Actions

Fraol Batole, Foutse Khomh, and Hridesh Rajan

In 2026 IEEE/ACM International Conference on Automated Software Engineering (ASE), 2026

Bib PDF

@inproceedings{batole2026refineact,
  title = {RefineAct: Automatic Runtime Verification of LLM Agent Actions},
  author = {Batole, Fraol and Khomh, Foutse and Rajan, Hridesh},
  year = {2026},
  booktitle = {2026 IEEE/ACM International Conference on Automated Software Engineering (ASE)},
  publisher = {ASE},
  organization = {IEEE},
}

FSE’25

IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models

Sayem Mohammad Imtiaz, Astha Singh, Fraol Batole, and 1 more author

In ESEC/FSE’2025: The 33st ACM Foundations of Software Engineering, Trondheim, Norway, Jun 2025

arXiv Bib PDF

@inproceedings{imtiaz2025irepair,
  author = {Imtiaz, Sayem Mohammad and Singh, Astha and Batole, Fraol and Rajan, Hridesh},
  title = {IRepair: An Intent-Aware Approach to Repair Data-Driven Errors in Large Language Models},
  booktitle = {ESEC/FSE'2025: The 33st ACM Foundations of Software Engineering},
  location = {Trondheim, Norway},
  month = jun,
  year = {2025},
}

TSE’26

Typestate-based Fault Localization of API Usage Violations in a Deep Learning Program

Fraol Batole, Ruchira Manke, Robert Dyer, and 2 more authors

IEEE Transactions on Software Engineering, Jan 2026

Journal-First presentation at FSE’2026 (Published in IEEE Transactions on Software Engineering)

Bib PDF

@article{batole2026neuralstate,
  author = {Batole, Fraol and Manke, Ruchira and Dyer, Robert and Nguyen, Tien N. and Rajan, Hridesh},
  title = {Typestate-based Fault Localization of API Usage Violations in a Deep Learning Program},
  journal = {IEEE Transactions on Software Engineering},
  note = {Journal-First presentation at FSE'2026 (Published in IEEE Transactions on Software Engineering)},
  month = jan,
  year = {2026},
}