English

An Executable Benchmarking Suite for Tool-Using Agents

Software Engineering 2026-05-13 v1 Artificial Intelligence Multiagent Systems

Abstract

Closed-loop tool-using agents are increasingly evaluated in executable web, code, and micro-task environments, but benchmark reports often conflate workloads, action-generating drivers, and the evidence admitted for systems-facing claims. We present an executable benchmarking suite that makes these objects explicit under a shared evidence-admission contract. The suite connects WebArena Verified, a SWE-Gym slice with SWE-bench-compatible verification, and MiniWoB++ through common workload adapters, task manifests, event schemas, replay/freeze policy, declared drivers, and reporting pipelines. In the canonical release, the gate separates paper-facing evidence from preflight, fixture, smoke, and diagnostic rows while preserving non-admitted artifacts for audit and onboarding. The admitted evidence records latency, invalid-action behavior, patch-generation cost, verifier metadata, replay bindings, and provenance under one auditable contract. The gate is decision-relevant rather than merely clerical: in a separate WebArena Verified controller study, clean-baseline and medium live-stressed evaluation select different fixed controller variants under the same workload and admission contract. The release is scoped as a benchmarking suite and admitted evidence, not a new agent policy, model leaderboard, backend comparison, or autonomous SWE-bench solver.

Keywords

Cite

@article{arxiv.2605.11030,
  title  = {An Executable Benchmarking Suite for Tool-Using Agents},
  author = {Zhiqing Zhong and Zhijing Ye and Jiamin Wang and Xiaodong Yu},
  journal= {arXiv preprint arXiv:2605.11030},
  year   = {2026}
}

Comments

20 pages, 2 figures, 20 tables, including appendices