arXiv cs.AI· Yuchen Ling, Shengcheng Yu, Zhenyu Chen, Chunrong Fang·· 6 天前AI 评分36
Jev 加速智能体决策的实证研究：更快决策未必带来更好智能体
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 两个场景、五类智能体、4500 次任务执行中评估 Jev 对决策效率的影响，发现 Jev 显著降低决策成本与延迟，但任务级收益因工作流而异。ALFWorld 任务成功率接近基线，两个移动端智能体成功率明显下降，辅助推理与额外交互吸收了决策节省，失败恢复与过早完成限制交付，某智能体单次尝试成本下降但每个成功结果的平均成本反而上升。
正文 · 原文
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