Agentic Engineering (AE+X)

My 3–5 year agenda is Agentic Engineering (AE+X): the goal is not only to use AI/LLMs, but to design, evaluate, and deploy multi-agent architectures that deliver reliable outcomes in real workflows.

Key themes:

• Evaluation and benchmarking for agentic systems (reliability, calibration, failure analysis)
• Reproducible pipelines for human/LLM hybrid coding and quality assurance
• Governance as a first-class output (documentation, auditability, responsible AI)

Selected outputs & working papers (2025+)

• Hierarchical Error Correction for Large Language Models: A Systematic Framework for Domain-Specific AI Quality Enhancement

  Cite / Share

  Export

  Copy citation Copy link Copy BibTeX BibTeX Copy RIS RIS Copy CSL-JSON CSL-JSON

  Share

  Copy share text X LinkedIn

  Tip: listen to the two-host audio overview above for a quick, conversational walkthrough, then share the link + citation.
  (2025)— Submitted
  Listen: audio overview

  Tip: the player loads audio only when opened, to keep the page fast.

  Take-home: A systematic, multi-level error-correction workflow that improves the robustness of domain-specific AI/LLM outputs.

  Prefer listening to reading? The audio overview gives a short, two-host walkthrough of the paper’s core question, method, and key finding.
• Automated Quality Assessment for LLM-Based Complex Qualitative Coding: A Confidence-Diversity Framework

  Cite / Share

  Export

  Copy citation Copy link Copy BibTeX BibTeX Copy RIS RIS Copy CSL-JSON CSL-JSON

  Share

  Copy share text X LinkedIn

  Tip: listen to the two-host audio overview above for a quick, conversational walkthrough, then share the link + citation.
  (2025)— Submitted
  Listen: audio overview

  Tip: the player loads audio only when opened, to keep the page fast.

  Take-home: A practical way to assess (and calibrate) the reliability of LLM-based complex qualitative coding using a confidence–diversity lens.

  Prefer listening to reading? The audio overview gives a short, two-host walkthrough of the paper’s core question, method, and key finding.
• A Confidence–Diversity Framework for Calibrating AI Judgement in Accessible Qualitative Coding Tasks

  Cite / Share

  Export

  Copy citation Copy link Copy BibTeX BibTeX Copy RIS RIS Copy CSL-JSON CSL-JSON

  Share

  Copy share text X LinkedIn

  Tip: listen to the two-host audio overview above for a quick, conversational walkthrough, then share the link + citation.
  (2025)— Revise & resubmit
  Listen: audio overview

  Tip: the player loads audio only when opened, to keep the page fast.

  Take-home: A confidence–diversity framework for calibrating AI judgement in accessible qualitative coding tasks, balancing accuracy with uncertainty awareness.

  Prefer listening to reading? The audio overview gives a short, two-host walkthrough of the paper’s core question, method, and key finding.
• Visual Orientalism in the AI Era: From West-East Binaries to English-Language Centrism

  Cite / Share

  Export

  Copy citation Copy link Copy BibTeX BibTeX Copy RIS RIS Copy CSL-JSON CSL-JSON

  Share

  Copy share text X LinkedIn

  Tip: listen to the two-host audio overview above for a quick, conversational walkthrough, then share the link + citation.
  (2025)— Submitted
  Listen: audio overview

  Tip: the player loads audio only when opened, to keep the page fast.

  Take-home: In the AI era, “orientalism” shifts from simple West–East binaries toward a subtler English-language centrism that structures visibility and authority.

  Prefer listening to reading? The audio overview gives a short, two-host walkthrough of the paper’s core question, method, and key finding.

See also: the full research portfolio with cite/export tools on Research.