Research
Research that becomes working systems.
My research work is centered on intelligent agents, semantic communication, negotiation, and grounded AI workflows. I use implementation as part of the research process so protocols, assumptions, and failure modes can be inspected rather than remaining only conceptual.
T1
Semantic interoperability
How independently designed agents can communicate when their concepts and ontologies do not align beforehand.
T2
Protocol-driven interaction
Making negotiation and coordination inspectable through explicit states, message flows, and constrained dialogue.
T3
Grounded AI systems
Designing workflows where generated conclusions remain traceable to source evidence and intermediate processing.
T4
Observable agent architecture
Treating tracing, state transitions, and communication paths as core engineering concerns, not afterthoughts.
Research systems
FLAGSHIP
STRATON-LLM
An ontology-based communication and semantic negotiation system for heterogeneous intelligent agents that do not share the same terminology or prior knowledge of one another.
FLAGSHIP
LATTICE Framework
An open, domain-agnostic multi-agent framework for decentralized collaboration between specialized autonomous agents.
Grounded AI
Research-Paper Deconstruction Agent
A two-stage system that reconstructs research PDFs into structured Markdown/JSON and runs a LangGraph multi-agent workflow for source-grounded technical analysis.
05 Apr 2026 · 8 min read
Designing Semantic Negotiation for Heterogeneous Intelligent Agents
Why STRATON-LLM treats ontology mismatch as a negotiation problem rather than a simple alignment problem, and how the end-to-end system is structured.
04 Apr 2026 · 7 min read
Why Ontology Alignment Alone Is Not Enough for Real Agent Interoperability
Ontology alignment helps agents find candidate correspondences, but real interoperability needs context, confidence handling, negotiation, and post-dialogue evaluation.
03 Apr 2026 · 8 min read
How Protocol-Governed Dialogue Makes LLM-Supported Negotiation Inspectable
The protocol engine is the control spine of STRATON-LLM. It turns negotiation from a free-form exchange into a replayable, rule-bound process.
02 Apr 2026 · 7 min read
Evaluating Agent Agreements with Dialogue-Aware Trust Heuristics
STRATON-LLM evaluates the quality of an agreement by scoring the dialogue that produced it, not just the final answer.