返回首页
arXiv AI··论文与技术

On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents

中文摘要

中国:研究人员探讨时间预算下LLM代理的效率,关注其遵守时限及有效利用时间的能力。

English Summary

English: Researchers explore the efficiency of LLM agents under time budgets, focusing on their ability to adhere to deadlines and use time productively.

原文节选

arXiv:2610.10833v1 Announce Type: new Abstract: We study whether small LLM agents can operate effectively under explicit wall-clock time budgets by both respecting the allocated runtime and using available time productively. We evaluate Qwen3.6-27B on five competitions from MLE-Bench Lite and Qwen3-4B on Zork I (Jericho), two agentic benchmarks where additional computational time can meaningfully improve performance. In the simplest setting, where the budget is stated only in the prompt, agents fail to translate the stated budget into controlled use of time. These failures arise from gaps in time awareness, since the harness provides no timing feedback, but also because they cannot reliably anticipate the duration of actions, and do not have a learned mapping from available time to an appropriate strategy. We investigate two complementary classes of interventions: harness-based mechanisms that expose timing information and enforce deadlines, and reinforcement learning with budget-aware rewards. Injecting timing information through the harness substantially improves budget adherence for Qwen3.6-27B without measurable loss in performance, while enforcement hooks tighten adherence fur…