{"ID":3084752,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-07T00:57:50.230973856Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.05557","arxiv_id":"2606.05557","title":"AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents","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 \u003c 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.","short_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 th...","url_abs":"https://arxiv.org/abs/2606.05557","url_pdf":"https://arxiv.org/pdf/2606.05557v1","authors":"[\"Yang Li\",\"Jiaxiang Liu\",\"Jiang Cai\",\"Mingkun Xu\"]","published":"2026-06-04T01:11:06Z","proceeding":"cs.CL","tasks":"[\"cs.CL\"]","methods":"[\"Large Language Model\"]","has_code":false,"code_links":[{"ID":612856,"CreatedAt":"2026-06-05T06:46:15.197025399Z","UpdatedAt":"2026-06-05T06:46:15.197025399Z","DeletedAt":null,"paper_id":3084752,"paper_url":"https://arxiv.org/abs/2606.05557","paper_title":"AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents","repo_url":"https://github.com/innovation64/AURA","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}