HIVEMIND:Human-centred collaboratIVE MultI-ageNt framework for accelerating software Development and maintenance
Status:
Start date:
End date:
HIVEMIND is an ambitious project aiming to advance responsible and human-centric software engineering methods, tools and best practices leveraging AI and data technologies to accelerate the whole software development lifecycle. To this end, the project introduces an adaptive LLM-based multi agent framework that enables collaboration between human actors and multiple AI agents
tailored to mirror and provide specialised support for the various roles within a traditional software development team.
| First Name | Last Name | Title |
|---|---|---|
| Mobyen Uddin | Ahmed | Professor |
| Shahina | Begum | Professor |
| Shaibal | Barua | Senior Lecturer |
Explaining Agent Interactions through their Causal Behavior and Counterfactuals (Oct 2026) Mir Riyanul Islam, Shaibal Barua, Mobyen Uddin Ahmed, Shahina Begum 27th Engineering Applications and Advances of Artificial Intelligence (EAAAI26)
Evaluating AI Agent Prompting and Fine-Tuning Strategies for Structured Data Extraction from Industrial PDFs (Sep 2026) Md Masum Billah , Mobyen Uddin Ahmed, Shaibal Barua, Nicolas Leberruyer , Shahina Begum ARRAY (ARRAY)
Mechanistic Interpretability of Transformer MLPs Through Exact Soft‑Gate Decomposition (Sep 2026) Arnab Barua, Mobyen Uddin Ahmed, Shahina Begum Transactions on Machine Learning Research (TMLR)
