Author

Hang Lyu

h-index 0 View on Semantic Scholar

6 papers indexed here

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.

Preprint Oct 2026

Who Speaks, Who Authorizes, Who Acts? Understanding Trust Boundaries in Multi-Agent LLMs

Multi-agent LLM systems exchange messages before acting through tools, but message delivery, signing authority, and tool-side enforcement are separate trust boundaries. We represent them as communication, authorization, and execution structures, and use the authority cut to characterize the smallest independently compr...

Jun-Ru Zhu, Xin Chen, Hang Lyu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Knowing When to Yield: Grounded Arbitration of User Corrections in Text-Based Embodied Agents

How should an embodied agent respond when a person's correction may be wrong? We formulate grounded correction arbitration as a choice among accepting, rejecting, inspecting the world, and asking the speaker. GAVA implements this interface with observation-bounded evidence, legal probes, and a one-step expected-loss ru...

Ye-Zhou Cheng, Run-Jia Du, Ze-Ming Liu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Scope Before You Persist: Preventing Cross-Family Interference in Agent Memory

These results establish scope matching as a complementary control for persistent agent memory: certification determines whether an edit is supported, while retrieval scope determines where that evidence authorizes its use.

Ye-Zhou Cheng, Run-Jia Du, Ze-Ming Liu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

Sharp Limits for Honest Uncertainty in Hard-Budget Repeated Evaluation

Repeated evaluation can estimate a benchmark score accurately while still requiring replication to certify narrow uncertainty. We characterize that requirement on a fixed grid of $M$ tasks with $L$ binary paths per task under the hard budget $(M+t)K$, where each path costs at most $K$ responses or episodes. For fixed $...

Ye-Zhou Cheng, Run-Jia Du, Ze-Ming Liu et al. · 0 citations

#artificial intelligence Preprint Sep 2026

LWCal: Loss-Weighted Calibration for Tabular Classifiers with Noisy Calibration Labels

LWCal is proposed, a CPU-only post-hoc calibrator that down-weights calibration examples whose noisy labels are contradicted by the base model's held-out probability.

Ze-Ming Liu, Hang Lyu, Jing-Tao Zhang et al. · 0 citations

Preprint Aug 2026

FaultLens: Learning Compact Behavioral Test Suites for Generated Operational Programs

FaultLens is introduced, a method for learning compact behavioral test suites while preserving an auditable connection to executed evidence and provides a prioritized evidence mechanism, not a proof of correctness, and makes its budget, evidence source, generalization split, and misses explicit.

Zejun Liu, Hang Lyu, Jing-Tao Zhang · 0 citations