Skip to content

Author

W. Shu

We have 6 of 25 papers

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#artificial intelligence Preprint Sep 2026

Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift

Tool-using language-model agents can decide that an action is permissible and execute it only after security-relevant state has changed. We study this proposal-to-commit gap and introduce BSC-R, a deterministic effect-boundary mechanism that binds a single-use commit authorization to the exact action and to a semantic...

W. Shu · 0 citations
#artificial intelligence Preprint Sep 2026

Authority Before Utility: Non-Compensatory Control for Persistent LLM Memory

Persistent memory creates a control problem that retrieval relevance alone does not solve: a memory can remain highly useful after an update, deletion, or revocation makes it inadmissible for the current answer. We formalize this as a separation between utility and authority. A fixed finite penalty applied to an unnorm...

W. Shu · 0 citations
#artificial intelligence Preprint Sep 2026

Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance

Reasoning systems usually treat premise use as a question of relevance: if a fact is available and useful, it may be selected for inference. Authorization imposes a different constraint: a premise may be represented and logically usable but not permitted for a particular local transition. We formalize this distinction...

W. Shu, Hsiang Lin · 0 citations
#artificial intelligence Preprint Aug 2026

Reachable Global Optimization in AI Systems: How Global Is Global?

AI systems increasingly claim to optimize prompts, policies, architectures, plans, tool-use trajectories, reasoning traces, and test-time computation. This paper argues that such claims are underspecified unless they state the region actually reachable by the system that performed the optimization. We introduce Reachab...

W. Shu · 0 citations
Preprint Aug 2026

Second-Order Policy Effects as State Transitions: A Source-Linked Benchmark for Policy Simulation

Policy evaluation often estimates direct benefits and costs while treating the institutional environment as fixed. In practice, a policy changes the system it enters: actors adapt, enforcement capacity shifts, burdens move, and new equilibria form around capture, gaming, compliance theater, irreversibility, and repair...

W. Shu · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.