arXiv：cs.AI· Yuchen Ling, Shengcheng Yu, Zhenyu Chen, Chunrong Fang·· 13 小时前
Jev 集成到 Agent 工作流能否真正提升效率？arXiv 实证研究
When Faster Decisions Do Not Make Better Agents: An Empirical Study of Jev in Agent Workflows
AI 导读
研究在 ALFWorld 与 AndroidWorld 两类场景中对五个 Agent 做了 4,500 次任务执行，检验 Jev 带来的决策提速能否转化为可靠的任务完成。结果显示 Jev 普遍降低决策成本与延迟，但 ALFWorld 任务成功率仅接近基线，两个移动端 Agent 明显下降；辅助推理与额外交互吸收了节省，失败恢复与过早结束制约交付，某 Agent 每次成功结果的平均成本反而上升。
正文
Abstract:AI agents depend on repeated decisions to accomplish tasks, with large language models (LLMs) commonly serving as their core decision makers. The recent emergence of Jev offers an opportunity to make these decisions faster and at lower cost. However, it remains unclear whether such local savings can be translated into efficient and reliable task completion. In this paper, we investigate this efficiency transfer across five agents in two representative application settings, embodied tasks in ALFWorld and mobile app use in AndroidWorld. Across 4,500 task executions, we jointly evaluate task effectiveness, decision-level and task-level resource use, and execution behavior. Experimental results show that Jev integration substantially reduces decision cost and latency across all five agents, with task-level gains varying by workflow. Task success remains close to baseline levels on ALFWorld and declines more substantially in two mobile agents. Auxiliary reasoning and additional interactions absorb decision savings, while failed recovery and premature completion limit successful delivery. Mean cost per successful outcome increases in one agent even as spending per attempt falls. These findings highlight the importance of preserving progress, supporting recovery, and verifying completion when integrating efficient decision models into agent workflows. Their practical value should be assessed through successful task delivery, recovery behavior, and resources per delivered outcome.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.13092 [cs.AI] |
| (or arXiv:2610.13092v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13092 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Shengcheng Yu [view email]
[v1]
Fri, 9 Oct 2026 06:45:23 UTC (242 KB)
来源：arXiv：cs.AI · arxiv.org