IBM at Open Source Summit Korea 2026

Open source has been the single most powerful force democratizing AI—taking capabilities that might otherwise be confined to a handful of well-resourced labs and putting them within reach of researchers, developers, and IT operators everywhere. But the relationship runs both ways: as AI systems increasingly write and contribute code, they are reshaping the open-source ecosystem itself—straining how we manage a rising tide of machine-generated contributions and how we secure code in an era when both attackers and defenders are AI-augmented. In this keynote, I make the case for why open models and open technologies like PyTorch, vLLM, and llm-d are critical enablers for enterprises and governments seeking greater control and flexibility over their AI, and I highlight the technical innovation making this possible. I close by arguing that we have a real opportunity to turn this two-way street into a virtuous loop—building AI that accelerates and secures open source even as open source accelerates AI.

Speakers: Kevin Dubois, IBM & Carlos Sanchez, Adobe

Your software rollouts to production are probably always flawless, right? For the rest of us, once in a while we do run into issues when releasing code to production. Even with robust CI/CD, production rollouts can hit unexpected snags. While in Kubernetes, ArgoCD and Argo Rollouts excels at Progressive Delivery and automated rollbacks to mitigate deployment issues, what if we could go a step further?

This session explores how to elevate your release process by integrating Agentic AI and asynchronous coding agents, with Argo Rollouts canary deployments. We'll demonstrate how an intelligent agent can automatically analyze a rollout failure, pinpointing the root cause. Beyond diagnosis, these agents can take proactive steps on your behalf, suggesting and even implementing code fixes as new pull requests, which can be redeployed automatically after PR review. This approach moves us closer to truly self-healing deployments.

Join us to learn how to combine the power of cloud native projects like Kubernetes, ArgoCD and Argo Rollouts with the autonomous capabilities of Agentic AI, achieving a release experience that is not only seamless but also resilient.

When global AI development being centralized around proprietary "black-box" models, the demand for Sovereign AI has become a national priority for many countries, including South Korea. True sovereignty requires more than just local data or local LLMs; it demands independence across the entire stack—from silicon up to the software services, as well as AI model itself. This panel challenges the misconception that global technology leaders are incompatible with national goals, demonstrating instead how open-source collaboration is the only viable path to technical and data independence as foundation for Sovereign AI.

Panelists:

• Yongkook Kim, IBM
• Priya Nagpurkar, IBM
• Jae Lee, Rebellions
• Alice Oh, KAIST

Speakers: Alessandro Pomponio & Michael Johnston, IBM

As AI agents become increasingly capable of generating code and executing complex workflows, their use in research is still limited by concerns about rigour and reproducibility. This session introduces ado, an open-source framework that brings structure to agent-driven scientific experimentation.

ado defines schemas for the core elements of a discovery process: the problem space and how to explore it. Agents iteratively propose and refine experimental campaigns as validated configurations based on these schemas, while ado handles execution. This separation of research intent from execution constrains agents to focus on the research task, reducing hallucinations and the need to write boilerplate code. Combined with a set of agent skills for formulating problems, creating and running experiments, and analysing their results, ado provides a framework for end-to-end agent-driven discovery workflows.

Whether you are an experienced researcher or new to computational experimentation, this talk presents a practical model for integrating AI agents into research workflows while keeping experimentation structured, transparent, and reproducible.

Speakers: KyoSeok Kim & Suyeon Woo, IBM

When enterprises bring AI into real-world operations, reliability challenges extend far beyond hallucinations and response accuracy. Document structure and meaning can be lost during processing, retrieval may fail to provide sufficient grounding, and models may violate business rules or operational constraints. As agents connect to enterprise systems, additional risks emerge, including unauthorized tool calls and actions that are difficult to trace or audit. These challenges cannot be addressed by adding a guardrail at the final stage. Reliability must be designed across the entire workflow, from document understanding and retrieval to reasoning, generation, and execution. This session presents an open-source reference architecture that combines document representation with Docling and DocLang, grounded retrieval and reasoning with OpenRAG and Granite, requirement-driven generation and validation with Mellea, and controlled, observable tool integration with ContextForge.

Speakers: Kevin Dubois, IBM & Daniel Oh, Red Hat

Agentic AI is all the hype right now, but how do you actually implement such a system for real enterprise, cloud based use cases?

The challenge for developers, architects and platform engineers alike lies in custom building agents, and even more so, orchestrating these agents to collaborate effectively towards a common goal. Unfortunately though, despite all the promises from vendors, a "one-size-fits-all" or “off-the-shelf” approach just doesn't work due to the complex nature of software. In addition, just like traditional apps, these agentic systems will likely need to be deployed, managed and observed in cloud environments.

In this session we'll explore:

• The spectrum of Agentic AI patterns

• A real world-ish implementation of a highly performant - open source - agentic system (with Java!)
• Deploying this agentic system to Kubernetes
• Other considerations such as observability and fault tolerance to get it all running smoothly in production.