collaborators

5 papers

cs.CR2026

Test-time reasoning effort and unauthorized tool use in language-model agents: a prespecified equivalence study

Xiaonan Xu, Wenjing Wu

Language-model agents that execute multi-step workflows through tool calls operate under access-control policies that restrict which operations each role may perform. The APIs serv…

cs.SE2026

Validation Evidence in LLM Repair Agents: How Much of What Passes Actually Tests the Bug?

Xiaonan Xu, Wenjing Wu

When a repair agent runs a test and sees it pass, the result is treated as evidence about the reported defect. We measure how often that treatment is warranted. BSG-VA (buggy-state…

cs.SE2026

Compression, structure, and executor capability: a controlled real-cost decomposition of language-model agent skill optimisation

Xiaonan Xu, Wenjing Wu

Agent skills, reusable instruction artefacts supplied to a tool-using language model, are increasingly optimised by shortening, structural rewriting, stronger-model compilation, an…

cs.CL2026

Skill Availability and Presentation Granularity in Large-Language-Model Agents: A Controlled SkillsBench Study

Xiaonan Xu, Wenjing Wu

Skill documents provide procedural knowledge to large-language-model agents at inference time. This article studies whether the presentation granularity of controlled skill knowled…

cs.MA2024

Large Language Model-Driven Cross-Domain Orchestration Using Multi-Agent Workflow

Xiaonan Xu, Haoshuo Chen, Jesse E. Simsarian +5

We showcase an application that leverages multiple agents, powered by large language models and integrated tools, to collaboratively solve complex network operation tasks across va…