3 papers
cs.SE2026
AiFlow: Token-Native Reactive Orchestration with Bounded Backpressure for Streaming LLM Applications
Qunhui Zhang
Large language model (LLM) applications increasingly operate as streaming workflows combining retrieval, tool calls, safety filters, and multi-agent coordination. Although contempo…
cs.PL2026
Generic Constraints Projection: Four-Dimensional Type Inference for Dynamic Languages
Qunhui Zhang
Type inference for dynamically typed languages must reconcile four qualitatively different sources of evidence: assigned values, explicit declarations, contextual requirements, and…
cs.PL2026
VirtualSet: Typed Ontology Worlds as an LLM Generation Target for Grounded Queries and Guarded Decisions
Qunhui Zhang
Large language models increasingly read and act on enterprise data, but SQL gives a late error signal: hallucinated fields or relations can execute and return plausible wrong answe…