Dialogue as Discovery: Navigating Human Intent Through Principled Inquiry

• URL: http://arxiv.org/abs/2510.27410v1
• Date: Fri, 31 Oct 2025 12:00:21 GMT
• Title: Dialogue as Discovery: Navigating Human Intent Through Principled Inquiry
• Authors: Jianwen Sun, Yukang Feng, Yifan Chang, Chuanhao Li, Zizhen Li, Jiaxin Ai, Fanrui Zhang, Yu Dai, Kaipeng Zhang,
• Abstract summary: A fundamental bottleneck in human-AI collaboration is the "intention expression gap"<n>We propose an agent that actively probes for information to resolve its uncertainty about user intent.<n>We name the proposed agent Nous, trained to acquire proficiency in this inquiry policy.
• Score: 38.72208780072353
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: A fundamental bottleneck in human-AI collaboration is the "intention expression gap," the difficulty for humans to effectively convey complex, high-dimensional thoughts to AI. This challenge often traps users in inefficient trial-and-error loops and is exacerbated by the diverse expertise levels of users. We reframe this problem from passive instruction following to a Socratic collaboration paradigm, proposing an agent that actively probes for information to resolve its uncertainty about user intent. we name the proposed agent Nous, trained to acquire proficiency in this inquiry policy. The core mechanism of Nous is a training framework grounded in the first principles of information theory. Within this framework, we define the information gain from dialogue as an intrinsic reward signal, which is fundamentally equivalent to the reduction of Shannon entropy over a structured task space. This reward design enables us to avoid reliance on costly human preference annotations or external reward models. To validate our framework, we develop an automated simulation pipeline to generate a large-scale, preference-based dataset for the challenging task of scientific diagram generation. Comprehensive experiments, including ablations, subjective and objective evaluations, and tests across user expertise levels, demonstrate the effectiveness of our proposed framework. Nous achieves leading efficiency and output quality, while remaining robust to varying user expertise. Moreover, its design is domain-agnostic, and we show evidence of generalization beyond diagram generation. Experimental results prove that our work offers a principled, scalable, and adaptive paradigm for resolving uncertainty about user intent in complex human-AI collaboration.

Related papers

• Interaction-Grounded Learning for Contextual Markov Decision Processes with Personalized Feedback [59.287761696290865]
  We propose a computationally efficient algorithm that achieves a sublinear regret guarantee for contextual episodic Markov Decision Processes (MDPs) with personalized feedback.<n>We demonstrate the effectiveness of our method in learning personalized objectives from multi-turn interactions through experiments on both a synthetic episodic MDP and a real-world user booking dataset.
  arXiv  Detail & Related papers  (2026-02-09T06:29:54Z)
• Steering LLMs via Scalable Interactive Oversight [74.12746881843044]
  Large Language Models increasingly automate complex, long-horizon tasks such as emphvibe coding, a supervision gap has emerged.<n>It presents a critical challenge in scalable oversight: enabling humans to responsibly steer AI systems on tasks that surpass their own ability to specify or verify.
  arXiv  Detail & Related papers  (2026-02-04T04:52:00Z)
• SelfAI: Building a Self-Training AI System with LLM Agents [79.10991818561907]
  SelfAI is a general multi-agent platform that combines a User Agent for translating high-level research objectives into standardized experimental configurations.<n>An Experiment Manager orchestrates parallel, fault-tolerant training across heterogeneous hardware while maintaining a structured knowledge base for continuous feedback.<n>Across regression, computer vision, scientific computing, medical imaging, and drug discovery benchmarks, SelfAI consistently achieves strong performance and reduces redundant trials.
  arXiv  Detail & Related papers  (2025-11-29T09:18:39Z)
• The Missing Reward: Active Inference in the Era of Experience [1.9761774213809036]
  Active Inference (AIF) provides a crucial foundation for developing autonomous AI agents.<n>AIF can replace external reward signals with an intrinsic drive to minimize free energy.<n>This synthesis offers a compelling path toward AI systems that can develop autonomously while adhering to both computational and physical constraints.
  arXiv  Detail & Related papers  (2025-08-07T17:57:12Z)
• When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration [79.69935257008467]
  We introduce Knowledge Integration and Transfer Evaluation (KITE), a conceptual and experimental framework for Human-AI knowledge transfer capabilities.<n>We conduct the first large-scale human study (N=118) explicitly designed to measure it.<n>In our two-phase setup, humans first ideate with an AI on problem-solving strategies, then independently implement solutions, isolating model explanations' influence on human understanding.
  arXiv  Detail & Related papers  (2025-06-05T20:48:16Z)
• Evaluations at Work: Measuring the Capabilities of GenAI in Use [28.124088786766965]
  Current AI benchmarks miss the messy, multi-turn nature of human-AI collaboration.<n>We present an evaluation framework that decomposes real-world tasks into interdependent subtasks.
  arXiv  Detail & Related papers  (2025-05-15T23:06:23Z)
• The Superalignment of Superhuman Intelligence with Large Language Models [63.96120398355404]
  We discuss the concept of superalignment from the learning perspective to answer this question.<n>We highlight some key research problems in superalignment, namely, weak-to-strong generalization, scalable oversight, and evaluation.<n>We present a conceptual framework for superalignment, which consists of three modules: an attacker which generates adversary queries trying to expose the weaknesses of a learner model; a learner which will refine itself by learning from scalable feedbacks generated by a critic model along with minimal human experts; and a critic which generates critics or explanations for a given query-response pair, with a target of improving the learner by criticizing.
  arXiv  Detail & Related papers  (2024-12-15T10:34:06Z)
• Towards Objective and Unbiased Decision Assessments with LLM-Enhanced Hierarchical Attention Networks [6.520709313101523]
  This work investigates cognitive bias identification in high-stake decision making process by human experts. We propose bias-aware AI-augmented workflow that surpass human judgment. In our experiments, both the proposed model and the agentic workflow significantly improves on both human judgment and alternative models.
  arXiv  Detail & Related papers  (2024-11-13T10:42:11Z)
• Optimising Human-AI Collaboration by Learning Convincing Explanations [62.81395661556852]
  We propose a method for a collaborative system that remains safe by having a human making decisions. Ardent enables efficient and effective decision-making by adapting to individual preferences for explanations.
  arXiv  Detail & Related papers  (2023-11-13T16:00:16Z)
• What Does The User Want? Information Gain for Hierarchical Dialogue Policy Optimisation [3.1433893853959605]
  optimisation via reinforcement learning (RL) is susceptible to sample inefficiency and instability. We propose the usage of an intrinsic reward based on information gain to address this issue. Our algorithm, which we call FeudalGain, achieves state-of-the-art results in most environments of the PyDial framework.
  arXiv  Detail & Related papers  (2021-09-15T07:21:26Z)
• Counterfactual Explanations as Interventions in Latent Space [62.997667081978825]
  Counterfactual explanations aim to provide to end users a set of features that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations. We present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations.
  arXiv  Detail & Related papers  (2021-06-14T20:48:48Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.