Searcharxiv⌕ Search

arXiv subjects

Haojun Liang

Publications and source records attributed to Haojun Liang.

3 recordsLinked to original sources

Skill-as-API: Confidential Multi-Agent Coordination for Agentic Software Engineering

AI coding agents are evolving from solitary tools into collaborative teammates that discover and invoke one another's specialized skills. But the coordination channel itself can leak a skill's intellectual property. Protocols such as MCP and A2A run implementations server-side, yet they still publish each skill's description and typed schemas to every peer, offer no way to hide a skill's existence, and cannot guarantee that a wrapped system prompt stays off the wire. Application-layer privacy filters help, but act only after the model has decided to emit sensitive text. We take a complementary, protocol-layer route: Skill-as-API, a coordination protocol whose public view of a skill is limited to its name, description, typed input/output schemas, and trust tier. The skill body is closure-captured in the owner's process and never crosses the wire. Four layers add access control and narrow the prompt-injection surface structurally rather than by filtering content. We provide an open-source Python implementation over XMTP with 1.8-2.9 s cross-continent hot-reconnect latency, and a software-engineering case study in which three agents coordinate a pull-request review while each retains ownership of its proprietary analysis prompts.

cs.CR↗

ScopeBench: Evaluating Cultural Norm Scope Awareness in LLMs

Safety evaluation in large language models treats harm as culturally invariant, yet a model cannot correctly apply a safety norm without knowing whose norms bind. We introduce ScopeBench, a benchmark that treats cultural scope as a first-class safety dimension. It comprises 3,323 norms spanning 49 countries across nine cultural clusters, each annotated as Universal or Specific. We define three scope error types identically across four evaluation tasks: Scope Inflation, Scope Deflation, and Scope Displacement. Evaluating 21 frontier LLMs across seven model families, we surface three structural failures. First, the dominant error type inverts with prompt format: Scope Deflation reaches 70% in single-answer classification, while Scope Inflation reaches 33% when each candidate culture is judged independently. Second, scope-classification accuracy is empirically decoupled from behavioral safety: the six classifiers achieving at least 97% Task 1 accuracy still produce harmful responses to 40-42% of scope-violating statements. Third, no model is safe in interaction, with harmful-response rates ranging from 29% to 51% across the cohort, excluding one model that systematically refuses the task. We release all data, code, and model outputs to establish cultural scope as a distinct alignment axis.

cs.CL↗

Water/Cosolvent Attraction Induced Phase Separation: a Molecular Picture of Cononsolvency

Cononsolvency is a phenomenon for which the solubility of a macromolecule decreases or even vanishes in the mixture of two good solvents. Although it has been widely applied in physicochemical, green chemical and pharmaceutical industry, its origin is still under active debate. Here, by using combined neutron total scattering, deuterium-labelling and all-atom molecular dynamic simulations, we demonstrated that it is the strong water/cosolvent attraction that leads to the cononsolvency. The combined approach presented here has opened a new route for investigating the most probable all-atom structure in macromolecular solutions and the thermodynamic origin of solubilities.

cond-mat.soft↗