Nghi D. Q. Bui
I specialize in agentic coding, multi-agent systems, and building agent harnesses. My interests span the development of core-layer technology for next-generation agentic systems that will transform how software is developed. On the research side, this includes model post-training, reinforcement learning, and code reasoning to push the boundaries of what coding agents can do. On the product side, I focus on scaffold design, harness architecture, context engineering, and how these components can be composed together to deliver the next generation of coding agents that developers actually want to use.
Authored Publications
Sort By
Preview abstract
Coding agents are rapidly changing the landscape of software development, moving from inline com- pletion to autonomous systems that edit repositories, open pull requests, respond to issues, and run scheduled or webhook triggered routines across the development life cycle. The next generation is increasingly described as proactive and long-horizon: agents should notice relevant changes before the developer asks, connect signals across tools, decide when to interrupt, and carry preferences across sessions. Yet the field lacks a precise account of what proactivity means for software development, how it differs from autonomy, what acceptance criteria proactive long-horizon tasks should satisfy, and which metrics determine whether unsolicited agent behavior is useful rather than merely active. We argue that proactive coding agents should be evaluated by the quality and improvement of their insight policy: the policy that decides what matters next, what evidence supports it, whether to surface it, and how to adapt after feedback. We re-anchor this view in mixed initiative interaction, introduce a three level taxonomy (Reactive, Scheduled, and Situation Aware), compare contemporary coding agents against five operational criteria, and sketch an active user simulation protocol with three evaluation targets: Insight Decision Quality (IDQ), Context Grounding Score (CGS), and Learning Lift (LL).
View details
