UDTR Global Radar

UDTR Global Rights of Nature Radar

Documentary registry of records detected across the scholarly, legal and institutional infrastructures monitored by UDTR.

A global documentary infrastructure designed to achieve the broadest verifiable and scientifically defensible coverage of the Rights of Nature.

← Back to Radar

AgentTime: Can Agents Estimate and Control Their Own Runtime?

Identification

Public canonical key
radar:r-076a433a78f8e00972284436374e85df
Authors
Michael Ofengenden · Maksym Andriushchenko
Reported year
2026
Reported language
en
Source type
preprint
First detected
2026-11-13T08:40:24.659126+00:00
Last metadata observation
2026-11-13T08:40:24.659126+00:00
Last HTTP verification
Not checked

Institutions reported by the source

Max Planck Institute for Intelligent Systems · Tübingen AI Center · ELLIS Institute Tübingen

Reported affiliation countries

DE

Documentary abstract — original language

An essential control of AI agents is their ability to manage runtime. This ability requires a sense of time-awareness, to predict and estimate wall-clock time and to control their own actions. Prior work has focused on time-awareness, but duration-following and control in native agent harnesses remain unexplored. We present AgentTime, a benchmark for testing whether agents can work for a requested duration, predict their runtime, and estimate elapsed time afterward. It comprises 222 tasks from 18 sources spanning coding, computer use, agentic work, and automated research. Duration-following experiments append a single instruction specifying how long to work, with requests ranging from about a minute to multiple days. Accuracy on these instructions varies substantially: Fable 5.1 in Claude Code deviates from requested runtimes by a typical factor of 2.9$\times$, compared with only 1.2$\times$ for GPT-6 Astra in Codex. However, matching the requested runtime does not, by itself, establish continued work on the task. Among 158 reviewed Astra runs with classifiable transcripts, 14 explicitly slept after appearing to finish. In forecasting experiments, predictions tend to overestimate natural runtimes. In retrospective experiments, removing temporal information more than doubles deviation for Sol and Astra and nearly doubles it for Fable. An agent's ability to complete a task does not guarantee that it can control its own time or work for the whole requested duration. For agents to run reliably, safely, and autonomously over long horizons, we require the evaluation of both.

Identifiers

OPENALEX
https://openalex.org/W7220971497
DOI
10.48550/arxiv.2610.09944

Documentary context

Documentary family
unknown
Source-reported types
preprint

Entity mentions are not evidence of legal recognition. Jurisdiction studied is separate from author affiliation country.

Sources

OpenAlex · Record 1

Cite this reference

Michael Ofengenden; Maksym Andriushchenko. AgentTime: Can Agents Estimate and Control Their Own Runtime?. 2026. https://doi.org/10.48550/arxiv.2610.09944

JSON · CSL-JSON · BibTeX · RIS · CSV · JSON-LD ·

APA, Chicago, ISO 690: bibliographic formats using available fields. OSCOLA / Bluebook: structured data only; full legal citation compliance is not claimed without verification of required elements.

APA
Michael Ofengenden; Maksym Andriushchenko. (2026). AgentTime: Can Agents Estimate and Control Their Own Runtime?. https://doi.org/10.48550/arxiv.2610.09944
Chicago
Michael Ofengenden; Maksym Andriushchenko. AgentTime: Can Agents Estimate and Control Their Own Runtime?. 2026. https://doi.org/10.48550/arxiv.2610.09944
ISO 690
Michael Ofengenden; Maksym Andriushchenko. AgentTime: Can Agents Estimate and Control Their Own Runtime?. 2026. https://doi.org/10.48550/arxiv.2610.09944

Warning: Undefined array key "last_link_verified" in /home/clients/e27d81e12f04d2bfd747aa264540ac56/sites/_UDTR_APP/legal_library_reference.php on line 31

UDTR Global Rights of Nature Legal Library. AgentTime: Can Agents Estimate and Control Their Own Runtime?. Documentary record: https://www.declarationuniverselledesdroitsdelarbre.org/global-rights-of-nature-radar/reference/r-076a433a78f8e00972284436374e85df/ · Last HTTP verification: not performed

Report a correction

Frozen-version metadata

Research dossiers and documentary relations

Source roles

Bibliographic / original publication source · https://arxiv.org/abs/2610.09944

An authority link alone does not verify a legal claim. Abstracts and full texts remain subject to their source terms.

Documentary status

Relevance pending

Library

This identity is not yet included in the Legal Library.

UDTR Global Rights of Nature Legal Library