| title | AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents |
|---|---|
| authors | Yang Li, Jiaxiang Liu, Jiang Cai, Mingkun Xu |
| date | 2026-06-04 |
| venue | arXiv (preprint, not peer reviewed) |
| id | arXiv:2606.05557 |
| affiliation | Guangdong Institute of intelligent science and Technology |
| upvotes | 1 (Hugging Face Daily Papers, 2026-11-01) |
| links | abs pdf hf code |
| abstract | A situated query like "where is Lin Wei?" often encodes more than its literal content: the user may also want to know whether Lin Wei is free, in a good mood, or worth interrupting now. Standard tool-use agents answer the literal question and stop. AURA inserts an inference step between scene perception and tool use that produces an IntentFrame: a structured estimate of the implicit need with a scalar gap score that controls per-query probe budget and tool selection. On a 100-query four-scene implicit-intent benchmark, AURA improves implicit-need coverage over ReAct-style probing (Delta = +0.07, p < 10^-6); three of four scenes are individually significant, the gain reproduces on a second backbone, and a prompt ablation attributes the lift to gap calibration rather than answer memorisation. On factual lookup the controller trades raw accuracy for 82% fewer probes and zero forbidden-tool violations on a privacy-sensitive slice; scope conditions are detailed in Limitations. Code, simulator, and benchmark are released at https://github.com/innovation64/AURA. |
cite
@misc{li2026aura,
title={AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents},
author={Yang Li and Jiaxiang Liu and Jiang Cai and Mingkun Xu},
year={2026},
eprint={2606.05557},
archivePrefix={arXiv},
url={https://arxiv.org/abs/2606.05557}
}