1 citations · 1 across the 5 of their papers we have counts for
9 papers
Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations
Xiaobo Chen, Genliang Zhu, Ziyuan Wang +1
After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a release check on typical test inputs ships it. We report a preregistered…
Signed but Not Safe: Requirement Integrity in Multi-Agent LLM Handoffs
Xiaobo Chen, Genliang Zhu, Ziyuan Wang +1
Enterprise AI agents increasingly split a user's request across subagents and merge their results, and each handoff can summarize away, alter or ignore a requirement. We report a p…
Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents
Genliang Zhu, Chu Wang
Long-horizon tool-using AI agents create subgoals, replan, delegate work, and compose sibling results. Per-tool permission checks cannot establish that a changing goal graph remain…
Language-Conditioned Token and Reasoning Efficiency in Large Language Models: A Paired Cross-Lingual Study Protocol
Genliang Zhu, Chu Wang
Large language models incur language-dependent representation and inference costs, but existing comparisons often conflate input language, assigned observable-trace language, and a…
Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution
Genliang Zhu, Chu Wang
Long-running AI agents outlive initiating processes through credentials, delegated tasks, queues, callbacks, reservations, and provider-side operations. Cancellation, process exit,…
Versioned Transitive Dependency-Closure Binding and Operation-Time Effect Governance for Agent Skills: ClosureBound
Genliang Zhu, Chu Wang
Agent Skills combine instructions with files, packages, tools, models, and services, so operational identity can exceed a signed directory. Recursive or lazy dependencies may chang…
Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
Genliang Zhu, Chu Wang
Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection. We present Explanation-Bou…
Intent-Governed Tool Authorization for AI Agents
Genliang Zhu, Chu Wang
Tool-using AI agents commonly operate under integration credentials whose static permissions exceed a user's current request. We present Intent-Governed Access Control (IGAC), a se…
OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access
Genliang Zhu, Chu Wang, Ziyuan Wang +2
AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties…