Chengzhan Li

Phase-Scoped Query Layouts for Reference-Constrained Speculative Decoding

Speculative verification changes the execution geometry of a quantized target model and can change its greedy output. We present phase-scoped query-to-batch (QB) attention, a graph transformation that pairs query and mask views, shares key/value storage, and retains batched projections and feed-forward computation. Pha...

Phase-Scoped Query Layouts for Reference-Preserving Speculative Decoding

Reference-Preserving Speculative Decoding on Consumer Systems: Diagnosis, Repair Scope, and Measured Cost

Speculative decoding changes the numerical history of a quantized runtime as well as its execution cost. When an application requires a fixed ordinary greedy output, the runtime must establish where constraints are needed and whether the qualified design saves time. We connect local state/path diagnosis, phase-scoped r...

Agent Step Value: Probing the Observer Effect in Black-Box Traces

Agent Step Value (ASV), a replay framework that scores before/after states with a state-less LLM evaluator over a fixed candidate set, turns prompt sensitivity into a measured channel effect and localizes the largest rationale-conditioned losses to extraction and audit.

Agent Step Value: State-Transition Measurement with State-Grounded LLM Evaluators

Agent Step Value (ASV), a state-transition measurement framework that scores each observed action by the change it induces in a state-grounded evaluator’s distribution over fixed candidate outcomes, is introduced.