I am actively looking for research interns, and I co-supervise Ph.D. students with university partners. Please note that I currently do not have funding for paid positions, so internships are unpaid research assistantships. If you are interested in AI agents, code generation and software engineering, or retrieval-augmented generation, please check the recruiting information here.
News
2026I will serve as a Senior Area Chair for ACL 2027, an Area Chair for NAACL 2027, and a Senior Program Committee member for AAAI 2027.
10.2025I will serve as a Senior Area Chair for EACL 2026.
2025MapEval is selected as a spotlight at ICML 2025.
Research
Large language models have made natural language an interface to computation, yet they fail in ways users cannot easily detect: answers cite unsupported sources, generated code runs but returns wrong results, and agents act on outdated views of their environment. My guiding principle is to never let the model be its own only witness. An answer should be checked against its cited passages, a program against its specification and execution, and an action against observations of the environment it will change. My research builds these checks throughout an agent’s workflow, along three connected threads.
Attribution is a pipeline property, not a post-hoc citation. Provenance survives to the output only if valuation, retrieval, filtering, and generation each expose an auditable decision. Open-RAG turns an open LLM into a sparse mixture-of-experts that ignores distractors and decides when to retrieve; its Llama2-7B version outperforms ChatGPT-RAG and Self-RAG. FiLCo learns which context to keep, DelucionQA detects hallucination, and CoT-PoT reaches self-consistency from two samples. Xolver extends retrieval to agentic memory: past solutions, experiences, and skills become one evolving store the agent can retrieve from as it works. The same machinery runs in legal aid (Mina), cyber-threat intelligence (TechniqueRAG), and medical screening (DR-VQA).
The bottleneck is correctness, not fluency. Code can be executed and tested, so it is where agent outputs can be verified. RedCoder was among the first retrieval-augmented code generators; MapCoder extended it to a recall–plan–code–debug team of agents, and CodeSim verifies plans by simulation before code exists (95.1% on HumanEval). Xolver carries this to general problem solving with shared, evolving memory, and xCodeEval evaluates code by execution at scale. At repository scale, SWE-Xplorer reconciles parallel search paths (53.2% to 60.8% on SWE-Bench Verified), and our agents resolve issues through discussion and review real pull requests.
End-to-end code pipeline (figure from my research statement)
Grounded and Live AgentsGrounded · Environment
How does the agent act?
Instrument first, then build the agent. On maps, the web, GUIs, and charts, models recite state they cannot operate on. MapEval exposed a gap of more than 20 points to humans in geo-spatial reasoning and grew into MapAgent, SpatiaLab, and TimeSpot. WebOperator searches web actions while ranking them by reversibility, GUI-Primitives isolates screen grounding as the bottleneck for computer-use agents, AgentTell shows that browser-use agents leak information through behavioural side channels, and ChartQAPro and DashboardQA test agents on the charts and dashboards organizations reason with.
Safety, Security, and Trust of AgentsTrustworthy · Guardrails · across all three
Can the agent be trusted?
Trust has to be built in, then audited. Our critical review of LLM evaluation diagnoses why model comparisons mislead. X-Teaming red-teams multi-turn conversations with collaborating planner, attacker, and verifier agents; Poison with Style shows the code supply chain can be poisoned with almost no utility loss; AI Debate helps human judges assess disputed claims; and our agentic security survey and AgentTell map threats to agents, including behavioural side-channel leakage in browser-use agents.
Published at ACL, EMNLP, NAACL, EACL, COLM, TMLR, ICML, NeurIPS, and ICLR. Citation metrics from Google Scholar, as of October 2026. Full list on the publications page.
@misc{hosain20254xolver,
title = {{Xolver: Multi-Agent Generalist Problem Solving with Holistic Experience Learning}},
author = {Hosain, Md Tanzib and Rahman, Salman and Morol, Md Kishor and Parvez, Md Rizwan},
howpublished = {AI4Math Workshop at ICML 2026; under review},
year = {2026}
}
@inproceedings{shayekh2024openrag,
title = {{Open-RAG: Enhanced Retrieval Augmented Reasoning with Open-Source Large Language Models}},
author = {Islam, Shayekh Bin and Rahman, Md Asib and Hossain, K S M Tozammel and Hoque, Enamul and Joty, Shafiq and Parvez, Md Rizwan},
booktitle = {Findings of EMNLP 2024},
year = {2024}
}
@misc{Wang2023filco,
title = {{Learning to Filter Context for Retrieval-Augmented Generation}},
author = {Wang, Zhiruo and Araki, Jun and Jiang, Zhengbao and Parvez, Md Rizwan and Neubig, Graham},
howpublished = {Pre-print},
year = {2023}
}
@inproceedings{parvez2022ret-privacy,
title = {{Retrieval-Enhanced Data Augmentation for Question Answering on Privacy Policies}},
author = {Parvez, Md Rizwan and Chi, Jianfeng and Ahmad, Wasi Uddin and Tian, Yuan and Chang, Kai-Wei},
booktitle = {EACL 2023},
year = {2023}
}
@misc{dihan2026swexplorer,
title = {{SWE-Xplorer: Iterative Tree Search with Cross-Path Reconciliation for Autonomous Software Engineering}},
author = {Dihan, Mahir Labib and Hashem, Tanzima and Ali, Mohammed Eunus and Parvez, Md Rizwan},
howpublished = {Under review},
year = {2026}
}
@misc{hosain20254xolver,
title = {{Xolver: Multi-Agent Generalist Problem Solving with Holistic Experience Learning}},
author = {Hosain, Md Tanzib and Rahman, Salman and Morol, Md Kishor and Parvez, Md Rizwan},
howpublished = {AI4Math Workshop at ICML 2026; under review},
year = {2026}
}
@inproceedings{islam2025codesim,
title = {{CodeSim: Multi-Agent Code Generation and Problem Solving through Simulation-Driven Planning and Debugging}},
author = {Islam, Md Ashraful and Ali, Mohammed Eunus and Parvez, Md Rizwan},
booktitle = {Findings of NAACL 2025},
year = {2025}
}
@inproceedings{islam2024mapcoder,
title = {{MapCoder: Multi-Agent Code Generation for Competitive Problem Solving}},
author = {Islam, Md Ashraful and Ali, Mohammed Eunus and Parvez, Md Rizwan},
booktitle = {ACL 2024},
year = {2024}
}
@inproceedings{khan2023xcodeeval,
title = {{xCodeEval: An Execution-based Large-Scale Multilingual Multitask Benchmark for Code Understanding, Generation, Translation and Retrieval}},
author = {Khan, Mohammad Abdullah Matin and Bari, M Saiful and Do, Xuan Long and Wang, Weishi and Parvez, Md Rizwan and Joty, Shafiq},
booktitle = {ACL 2024},
year = {2024}
}
@inproceedings{parvez2021retrieval,
title = {{Retrieval Augmented Code Generation and Summarization}},
author = {Parvez, Md Rizwan and Ahmad, Wasi Uddin and Chakraborty, Saikat and Ray, Baishakhi and Chang, Kai-Wei},
booktitle = {Findings of EMNLP 2021},
year = {2021}
}
@inproceedings{wasi2026spatialab,
title = {{SpatiaLab: Can Vision-Language Models Perform Spatial Reasoning in the Wild?}},
author = {Wasi, Azmine Toushik and Faisal, Wahid and Rahman, Abdur and Anik, Mahfuz Ahmed and Shahriar, Munem and Topu, Mohsin Mahmud and Meem, Sadia Tasnim and Priti, Rahatun Nesa and Mitu, Sabrina Afroz and Hoque, Md. Iqramul and Ridoy, Shahriyar Zaman and Ali, Mohammed Eunus and Hawasly, Majd and Raza, Mohammad and Parvez, Md Rizwan},
booktitle = {ICLR 2026},
year = {2026}
}
@inproceedings{hasan2025mapagent,
title = {{MapAgent: A Hierarchical Agent for Geospatial Reasoning with Dynamic Map Tool Integration}},
author = {Hasan, Md Hasebul and Dihan, Mahir Labib and Ali, Mohammed Eunus and Parvez, Md Rizwan},
booktitle = {Findings of EACL 2026},
year = {2026}
}
@inproceedings{dihan2025mapeval,
title = {{MapEval: A Map-Based Evaluation of Geo-Spatial Reasoning in Foundation Models}},
author = {Dihan, Mahir Labib and Hassan, MD Tanvir and Parvez, Md Tanvir and Hasan, Md Hasebul and Alam, Md Almash and Cheema, Muhammad Aamir and Ali, Mohammed Eunus and Parvez, Md Rizwan},
booktitle = {ICML 2025},
year = {2025}
}
@inproceedings{masry20254chartqapro,
title = {{ChartQAPro: A More Diverse and Challenging Benchmark for Chart Question Answering}},
author = {Masry, Ahmed and Islam, Mohammed Saidul and Ahmed, Mahir and others and Parvez, Md Rizwan and Hoque, Enamul and Joty, Shafiq},
booktitle = {Findings of ACL 2025},
year = {2025}
}
@inproceedings{masry2024chartinstruct,
title = {{ChartInstruct: Instruction Tuning for Chart Comprehension and Reasoning}},
author = {Masry, Ahmed and Shahmohammadi, Mehrad and Parvez, Md Rizwan and Hoque, Enamul and Joty, Shafiq},
booktitle = {Findings of ACL 2024},
year = {2024}
}
@article{dihan2025weboperator,
title = {{WebOperator: Action-Aware Tree Search for Autonomous Web Agents}},
author = {Dihan, Mahir Labib and Hashem, Tanzima and Ali, Mohammed Eunus and Parvez, Md Rizwan},
journal = {In submission to TMLR},
year = {2026}
}
@article{shahriar2026agenticsecurity,
title = {{A Survey on Agentic Security: Applications, Threats and Defenses}},
author = {Shahriar, Asif and Rahman, Md Nafiu and Ahmed, Sadif and Sadeque, Farig and Parvez, Md Rizwan},
journal = {TMLR 2026 (also AIWILD Workshop at ICLR 2026)},
year = {2026}
}
@inproceedings{tran2026pws,
title = {{Poison with Style: A Practical Poisoning Attack on Code Large Language Models}},
author = {Tran, Khang and Boshmaf, Yazan and Khalil, Issa and Phan, NhatHai and Yu, Ting and Parvez, Md Rizwan},
booktitle = {ICML 2026},
year = {2026}
}
@inproceedings{salman20254xteaming,
title = {{X-Teaming: Scalable Red-Teaming and Safeguarding of Interactive Multi-Turn Conversational AI Systems}},
author = {Rahman, Salman and Jiang, Liwei and Shiffer, James and Liu, Genglin and Issaka, Sheriff and Parvez, Md Rizwan and Palangi, Hamid and Chang, Kai-Wei and Choi, Yejin and Gabriel, Saadia},
booktitle = {COLM 2025},
year = {2025}
}
