This week, Xavier Franch from @upc.edu is attending #ICSE, #CAIN and #WSESE 2026.
On Monday 13, he presented a co-authored paper on AI agents in Agile project management.
👉 hivemind-project.eu
Software today powers everything, but building it is still complex, rigid, and time-consuming.
🤖 #HIVEMIND rethinks this by developing specialised AI agents that work alongside developers across the entire software lifecycle.
👉 More info: hivemind-project.eu
#AIagents
Get the latest from HIVEMIND. Subscribe to our biannual newsletter for a concise update on key developments and insights, delivered directly to your inbox. Stay informed and ahead of the curve.
đź“© by email: a06c99a4.sibforms.com/serve/MUIFAM...
đź’Ľ or on LinkedIn: www.linkedin.com/newsletters/...
Last week, HIVEMIND met with AI4SWEng, MOSAICO and ASTIR. We started coordination discussions, aligning objectives, defining next steps, and exploring a joint alliance. The groundwork for collaboration is now in place.
More soon: hivemind-project.eu
Today, 24 March, the #HIVEMIND consortium held a mid-term Exploitation and IPR workshop, led by @australo.bsky.social. Partners reviewed key exploitable results, identified stakeholders and early adopters, and refined pathways for real-world impact.
👉 hivemind-project.eu
Interesting paper for those working with user feedback, AI and requirements engineering.
It explores how emotions in app reviews go beyond positive or negative. Understanding signals like trust or frustration can change how user needs are identified.
👉 hivemind-project.eu/resources/
Our consortium partner SUPSI is organising the session “Decision Making in Autonomous Multi-Agent Systems” at IFORS 2026 (Vienna, 12–17 July). Researchers in multi-agent systems, optimization and autonomous decision-making are invited to contribute. Abstract deadline: 15 March. www.ifors2026.at/home
Innovation rarely comes from a single mind. It grows through collaboration, debate and shared expertise. In #HIVEMIND, many of those ideas come from women working across research, engineering and coordination. Today we give them the visibility and credit they deserve.
In case you missed it: our partners at Universitat Politècnica de Catalunya tested what happens when AI agents debate instead of working alone.
Result? Accuracy jumped from 0.726 to 0.835, with clear gains for non-functional requirements.
Read the paper: hivemind-project.eu/resources/
In January, the HIVEMIND consortium met in Berlin for the M12 General Assembly. Partners reviewed progress across all work packages, consolidated the multi-agent architecture, and aligned on next steps towards M18.
👉 Read more: hivemind-project.eu/hivemind-m12...
Scientific research depends on who takes part in it and whose expertise is recognised. In #HIVEMIND, women contribute across research, software, and AI as part of everyday work. Read their reflections for the International Day of Women and Girls in Science:
hivemind-project.eu/women-contri...
Still relevant, still worth a watch. This short video shows how #HIVEMIND brings multi agent AI into real software development workflows, explaining the core idea, the role of AI agents, and where the system is already being applied.
👉 Watch it here: hivemind-project.eu/hivemind-exp...
Get the latest from #HIVEMIND. Subscribe to our biannual newsletter for a concise update on key developments and insights, delivered directly to your inbox.
Choose the format that suits you best:
đź“© by email: f981d420.sibforms.com/serve/MUIEAH...
đź’Ľ or on LinkedIn: www.linkedin.com/newsletters/...
We’ve just wrapped up a productive HIVEMIND GA in Berlin. Partners reviewed progress across all work packages, aligned on what “agents” mean in HIVEMIND, and agreed on next steps towards M18, with a focus on implementation, integration, and reuse. Thanks to our hosts at @dfki.bsky.social!
The HIVEMIND consortium is meeting in Berlin today and tomorrow (21–22 January) for our General Assembly, hosted by DFKI.
Day one focuses on the base framework, core agents, and the year 2 work plan, with parallel sessions on training data, human feedback, and architecture.
hivemind-project.eu
AI can support software testing, but it cannot yet replace human judgement. Our partners’ research indicates that AI-assisted testing tools bring clear benefits, but their limits remain significant.
👉Access the paper in the resources section of our website: hivemind-project.eu/resources
#HIVEMIND
As the year gets underway, it is a good moment to pause and look at what #HIVEMIND has built so far. If you missed it, our latest newsletter revisits the first year of coordinated development that laid the foundations for the work ahead.
đź“©Subscribe for future updates: bit.ly/49JYSus
HELLO, WORLD! Wishing our partners, collaborators, and followers a restful holiday break. Thank you for being part of #HIVEMIND’s first year.
👉 hivemind-project.eu
HIVEMIND’s first year set the foundations of a responsible multi-agent ecosystem. The consortium worked across architecture, interaction, ethics and data to build a coherent base for the agents ahead.
Full article: hivemind-project.eu/one-year-of-...
HIVEMIND’s first year, wrapped. The second issue of our newsletter with the latest project updates is out.
If you’re curious about where #HIVEMIND currently stands, it’s all there: zenodo.org/records/1787...
And don’t forget to subscribe if you haven’t yet: hivemind-project.eu/newsletter/
The University of Alicante contributes to HIVEMIND’s first year with the development of the HCI guideline. It defines how users will engage with the agents, keeping human judgement central and interaction safer and more effective.
Full recap: hivemind-project.eu/one-year-of-...
#ResponsibleAI
We’re continuing our look back at HIVEMIND’s first year. Mälardalen University analysed leading agent frameworks, exposed gaps in fairness and transparency and outlined an ethical-agent architecture with traceability and human oversight.
Full recap: hivemind-project.eu/one-year-of-...
One year of #HIVEMIND offers a clear view of how the project has grown.
idener led this first phase by defining the system architecture and technical base for the agents ahead, setting the ground for a responsible multi-agent ecosystem.
Read more: hivemind-project.eu/one-year-of-...
In Germany, Fraunhofer IWU leads a #HIVEMIND use case applying digital twins to improve efficiency and energy optimisation in manufacturing.
AI agents will align code, solve compatibility issues, and optimise deployment, cutting dev time by 40%: hivemind-project.eu/use-cases/
#AIagents
Get the latest from HIVEMIND.
Subscribe to our biannual newsletter for a concise update on key developments and insights, delivered directly to your inbox. Stay informed and ahead of the curve.
👉 Sign up here: bit.ly/4lX1NEn
What can generative models reveal about the real data they learn from? This study by @upm.es researchers explores membership inference attacks in generative models, introducing new theory and showing how differential privacy fits in. A critical read for privacy-aware AI: synthema.eu/publications/
@qubelfastofficial.bsky.social leads a #HIVEMIND use case improving reliability in autonomous driving systems.
AI agents will generate compliant code, automate testing, and detect vulnerabilities early, cutting dev time by 40%: hivemind-project.eu/use-cases/
#AI #AutonomousVehicles
HIVEMIND is rethinking the future of software engineering through AI collaboration, openness and responsibility.
Discover more about the project:
👉 hivemind-project.eu
@dfki.bsky.social @australo.bsky.social @ua.es @upc.edu @qubelfastofficial.bsky.social
Software that learns from itself. HIVEMIND’s AI can detect issues, suggest solutions and optimise performance, paving the way for self-repairing systems built on trust and transparency.
Reliable software means trustworthy software. HIVEMIND integrates automated verification and testing tools that ensure every line of code performs as intended, safely and consistently.