mlsanityData to 7 Oct 2026

AURA: Intent-Directed Probing for Implicit-Need Surfacing in Situated LLM Agents

arXiv 2606.05557 ↗First posted 4 Jun 2026cs.CLcited by 0

On the map: LLM agents and tool use → Multimodal and embodied agents

Abstract (arXiv)

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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use. Builds on 24 of its 39 references that are in the map. First posted on arXiv 4 Jun 2026.

Builds on

24 of 39 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025ContextAgent: Context-Aware Proactive LLM Agents with Open-World Sensory Perceptions20 May

Other references · 23

  1. 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,160
  2. 2023Judging LLM-as-a-Judge with MT-Bench and Chatbot Arenacited by 8,393
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Toolformer: Language Models Can Teach Themselves to Use Toolscited by 4,072
  5. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,064
  6. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  7. 2023A Survey on Large Language Model based Autonomous Agentscited by 2,203
  8. 2023ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIscited by 1,880
  9. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  10. 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,348
  11. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  12. 2024Evaluating Very Long-Term Conversational Memory of LLM Agentscited by 800
11 more
  1. 2023SOTOPIA: Interactive Evaluation for Social Intelligence in Language Agentscited by 350
  2. 2023Large Language Models Fail on Trivial Alterations to Theory-of-Mind Taskscited by 288
  3. 2022Neural Theory-of-Mind? On the Limits of Social Intelligence in Large LMscited by 220
  4. 2025MultiAgentBench: Evaluating the Collaboration and Competition of LLM agentscited by 169
  5. 2023FANToM: A Benchmark for Stress-testing Machine Theory of Mind in Interactionscited by 162
  6. 2023Generative agent-based modeling with actions grounded in physical, social, or digital space using Concordiacited by 119
  7. 2023Minding Language Models' (Lack of) Theory of Mind: A Plug-and-Play Multi-Character Belief Trackercited by 95
  8. 2023T-Eval: Evaluating the Tool Utilization Capability of Large Language Models Step by Stepcited by 91
  9. 2023MAgIC: Investigation of Large Language Model Powered Multi-Agent in Cognition, Adaptability, Rationality and Collaborationcited by 56
  10. 2025CondAmbigQA: A Benchmark and Dataset for Conditional Ambiguous Question Answeringcited by 15
  11. 2026BMAM: Brain-inspired Multi-Agent Memory Frameworkcited by 3

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026IntentionNav: A Benchmark for Intent-Driven Object Navigation from Implicit Human Instruction
  2. 2026MM-ToolSandBox: A Unified Framework for Evaluating Visual Tool-Calling Agents
  3. 2025ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild
  4. 2024Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents
  5. 2026Do GUI Agents Believe Their Eyes? Diagnosing State-Belief Reliance on Pixels versus Structure
  6. 2026Making Every Tool Call Count: Necessary Tool-Evidence Path Rewards for Agentic Vision-Language Models
  7. 2026Diversity Over Frequency: Rethinking Tool Use in Visual Chain-of-Thought Agents
  8. 2025Beyond Facts: Evaluating Intent Hallucination in Large Language Models