Paper Detail
Yang Li, Jiaxiang Liu, Jiang Cai, Mingkun Xu
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.
No structured notes yet. Add `summary_sections`, `why_relevant`, `claim_impact`, or `next_action` in `papers.jsonl` to enrich this view.
No ranking explanation is available yet.
No tags.
@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},
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 im},
url = {https://huggingface.co/papers/2606.05557},
keywords = {IntentFrame, gap score, tool-use agents, ReAct-style probing, implicit-need coverage, probe budget, controller, gap calibration, code available, huggingface daily},
eprint = {2606.05557},
archiveprefix = {arXiv},
}
{}