12 papers
Boundary-State Control for Tool-Using Language-Model Agents: Commit-Time Consistency under State Drift
Wesley Shu
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 in…
Authority Before Utility: Non-Compensatory Control for Persistent LLM Memory
Wesley Shu
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 inadm…
Governed Deduction: Policy-Grounded Premise Authorization Beyond Relevance
Wesley Shu, Hsi-Ching Lin
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 const…
Reachable Global Optimization in AI Systems: How Global Is Global?
Wesley Shu
AI systems increasingly claim to optimize prompts, policies, architectures, plans, tool-use trajectories, reasoning traces, and test-time computation. This paper argues that such c…
Rank Portability Does Not Imply Feasibility Portability: Target-Specific Evaluation of Joint Hardware Constraints
Wesley Shu
Cross-device hardware evaluation often assumes that if architecture rankings transfer across devices, a proxy device can support target-side model selection. We stress-test this as…
Platform Adaptation Under Governance Interventions: Actor Best-Response Modeling and an External Public-Case Benchmark
Wesley Shu, Peng Wei
Digital platforms govern by changing rules: rankings, monetization thresholds, moderation standards, verification systems, disclosure requirements, appeal processes, and access pol…
Second-Order Policy Effects as State Transitions: A Source-Linked Benchmark for Policy Simulation
Wesley Shu
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,…
Validation-Frontier Representation Selection under Constrained Observation
Wesley Shu
AI systems deployed outside clean benchmark settings often rely on observations that are incomplete, unstable, costly, or degraded by monitoring failures. This paper studies repres…
Artificial Jagged Intelligence as Uneven Optimization Energy Allocation Capability Concentration, Redistribution, and Optimization Governance
Wesley Shu, Peng Wei
Artificial Jagged Intelligence (AJI) denotes a recurring pattern in which large learning systems exhibit strong local capabilities while remaining weak or brittle in other domains.…
AI Safety as Control of Irreversibility: A Systems Framework for Decision-Energy and Sovereignty Boundaries
Wesley Shu, Peng Wei
Recent AI systems compress the distance between capability growth and capability deployment. Earlier high-risk technologies were slowed by capital intensity, physical bottlenecks,…
Preserving Decision Sovereignty in Military AI: A Trade-Secret-Safe Architectural Framework for Model Replaceability, Human Authority, and State Control
Peng Wei, Wesley Shu
Recent events surrounding the relationship between frontier AI suppliers and national-security customers have made a structural problem newly visible: once a privately governed mod…
A Public Theory of Distillation Resistance via Constraint-Coupled Reasoning Architectures
Peng Wei, Wesley Shu
Knowledge distillation, model extraction, and behavior transfer have become central concerns in frontier AI. The main risk is not merely copying, but the possibility that useful ca…