Metraipolis › archive › dc_2a377aa71a57

On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents — arXiv:2610.10833

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.10833
License (as archived)
CC0-1.0
Archived
2026-10-09T05:47:16.115Z
SHA-256 of the archived text
7f97843ee4c172a3aa5717b1b082402094d01b4c04f580dfefb2c43ba6b3fcfd
Stable URL of this page
https://metraipolis.com/documento/dc_2a377aa71a57

How to cite

On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents — arXiv:2610.10833 — arXiv (en), https://arxiv.org/abs/2610.10833 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_2a377aa71a57 (Metraipolis archive dc_2a377aa71a57, sha256 7f97843ee4c172a3aa5717b1b082402094d01b4c04f580dfefb2c43ba6b3fcfd)
BibTeX
@misc{dc2a377aa71a57,
  title = {On the Clock: Towards Punctual and Productive Time-Budgeted AI Agents — arXiv:2610.10833},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.10833},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_2a377aa71a57; sha256 7f97843ee4c172a3aa5717b1b082402094d01b4c04f580dfefb2c43ba6b3fcfd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.10833. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 further. RL with GRPO achieves near-perfect budget adherence on Zork I and generalizes to held-out budgets not seen during training, but does not improve task performance over the untrained harness on MLE-Bench. Once agents are made to respect the budget, they still fail to use additional time to improve task performance. RL-trained policies learn when to stop but often fill extra time with repeated actions, and GRPO training on multiple budgets tends to collapse toward the strategy learned for the shortest budget. Our results reveal a gap between time adherence and productive time allocation, which remains a central challenge for budget-conditioned agents.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2610.10833 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-09T05:47:00.497Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).