ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Models
Temporal decisions in language-model systems often depend on both symbolic task state and elapsed wall-clock time, such as cache expiration, job completion, quota resets, deadlines, or stale sessions. We study whether elapsed time can be supplied as a non-token, system-side scalar and composed with visible symbolic state by a frozen-backbone language model. We introduce ChronoState, a compositional temporal-state benchmark in which symbolic state appears in the prompt, elapsed seconds tau are su
Record details
Published: 10 August 2026
Source: arXiv
Category: Research
Topics: Jobs & economy
Retrieved: 11 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
STAIR: Effective Incident Response Using an End-to-End Agentic Planning Framework
arXiv · 10 August 2026
GENCO - A Unified Neural Solver Embedded in a Development Framework for Steady-State Grid Analysis
arXiv cs.AI · 10 August 2026
Automated Features, Algorithms, and Technologies of Electronic Early Warning/Track-and-Trigger Systems: Systematic Review
JMIR (Journal of Medical Internet Research) · 10 August 2026
When the Interviewer Is a Bot: Behavior, Breakdowns, and Trust in MLLM-Led Interviews
arXiv cs.HC · 11 August 2026
How complementarities between automation and organisational innovation shape the wages of a firm's employees: The role of social skills
Technological Forecasting and Social Change · 9 August 2026
SCOUT: Symmetric Consensus Outlier Detection for Failure Localization in LLM Pre-Training
arXiv cs.LG · 11 August 2026
How to cite this record
ethics.ai (10 August 2026), “ChronoState: Hidden Elapsed-Time Conditioning for Temporal-State Action Selection in Frozen-Backbone Language Models,” evidence record 18027, https://ethics.ai/record/18027 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.