Long Quan Ton@longquanton
1
Events attended
1
Submissions made
Viet Nam
1 year of experience
About me
As an Artificial Intelligence major at the Joint Program between University of Technology Sydney (UTS) and Ho Chi Minh City University of Technology (HCMUT), I am an aspiring Agentic AI Engineer deeply passionate about the future of autonomous systems. My core technical focus lies at the intersection of Large Language Models (LLMs), Agentic AI and the Model Context Protocol (MCP). My primary goal is embedding intelligent, agentic systems into existing applications—particularly within the economic and engineering sectors. I thrive on architecting solutions that help companies seamlessly transition their traditional software ecosystems into dynamic, Agentic AI-driven platforms. I am constantly exploring new paradigms in AI and software architecture, and I am always open to connecting with forward-thinking professionals, engineers, and companies who are building the next generation of intelligent tech.
🤝 Top Collaborators
.png&w=640&q=75)
.png&w=640&q=75)
🤓 Latest Submissions
Develarper: Token-Efficient AI Agent
Develarper is an engineered containerized AI agent constructed for the AMD Developer Hackathon Track 1. It utilizes a highly optimized four-layer hybrid routing core to minimize total remote Fireworks API token consumption while clearing the required accuracy threshold. The agent dynamically routes tasks across eight distinct capability domains using zero-token heuristic overrides, localized semantic caching, and a supervised PyTorch MLP classifier utilizing all-MiniLM-L6-v2 embeddings to achieve 100% routing accuracy. Low-complexity tasks (such as sentiment analysis, NER, short summarization, and factual questions) are processed entirely local within the strict 4 GB RAM sandbox using an embedded Qwen2.5-3B model via llama-cpp-python. The architecture implements a "local-first" code execution path that tests code generation and debugging locally, using AST parsing validation before failing back to remote infrastructure. High-order deduction, mathematics, and long-context summaries are dynamically escalated to specialized remote models like kimi-k2p7-code and minimax-m3. Token trimming algorithms are applied globally to strip conversational filler and strictly compress input and output footprints, ensuring maximum token efficiency and robust leaderboard positioning.
13 Jul 2026
