Align AI to Dynamic Human-AI Workflows

• URL: http://arxiv.org/abs/2607.14240v1
• Date: Wed, 15 Jul 2026 18:02:03 GMT
• Title: Align AI to Dynamic Human-AI Workflows
• Abstract summary: We argue for a shift from static and emulative to interactive and complementary alignment.<n>We first formalize this gap by contrasting existing alignment with a trajectory-level view in which human and model behavior co-evolve over time.<n>We argue that human-AI systems amplify these dynamics, introducing new asymmetries that make reasoning about uncertainty harder.
• Score: 43.10610450289198
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Current alignment approaches typically focus on emulating human behavior using static representations of human preferences, failing to capture the dynamic, context-dependent nature of real-world human-AI interactions. In this paper, we argue for a shift from static and emulative to interactive and complementary alignment, where preferences emerge through interaction and alignment is defined not by satisfying preferences alone. We first formalize this gap by contrasting existing alignment with a trajectory-level view in which human and model behavior co-evolve over time. Because these interaction dynamics have not been adequately captured within existing ML formulations, we ground this perspective in insights from an interdisciplinary workshop. We draw on lessons from social-science accounts of human-human collaboration and then argue that human-AI systems amplify these dynamics, introducing new asymmetries that make reasoning about uncertainty harder and introduce new coordination challenges. Based on these lessons and new challenges, we conclude by outlining a research agenda for developing AI systems that align with humans in interaction, requiring an interdisciplinary synthesis of machine learning and the social and decision sciences.

Related papers

• Learning social norms enhances compatibility in dynamic human-AI coordination [22.247716743876214]
  Humans continuously coordinate with others in dynamic interactions, often through implicit, hard-to-quantify social norms.<n>As AI agents become embedded in daily life, they increasingly participate in such interactions and reshape social interaction structures.<n>We identify three principles underlying human social norms: outcome predictability, value alignment, and advantage awareness.
  arXiv  Detail & Related papers  (2026-07-08T05:39:08Z)
• Learning Whole-Body Human-Humanoid Interaction from Human-Human Demonstrations [63.80827184637476]
  We introduce D-STAR, a hierarchical policy that disentangles when to act from where to act.<n>We validate our framework through extensive and rigorous simulations.
  arXiv  Detail & Related papers  (2026-01-14T14:37:06Z)
• Human-AI Interaction Alignment: Designing, Evaluating, and Evolving Value-Centered AI For Reciprocal Human-AI Futures [27.995784716141767]
  The rapid integration of generative AI into everyday life underscores the need to move beyond unidirectional alignment models.<n>This workshop focuses on bidirectional human-AI alignment, a dynamic, reciprocal process where humans and AI co-adapt through interaction, evaluation, and value-centered design.
  arXiv  Detail & Related papers  (2025-12-25T07:45:38Z)
• Interactive AI and Human Behavior: Challenges and Pathways for AI Governance [3.799233413990495]
  Generative AI systems increasingly engage in long-term, personal, and relational interactions.<n>These Interactive AI systems adapt to users over time, build ongoing relationships, and even can take proactive actions on behalf of users.<n>This new paradigm requires us to rethink how such human-AI interactions can be studied effectively to inform governance and policy development.
  arXiv  Detail & Related papers  (2025-08-12T19:15:35Z)
• Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis [51.95817740348585]
  Human-X is a novel framework designed to enable immersive and physically plausible human interactions across diverse entities.<n>Our method jointly predicts actions and reactions in real-time using an auto-regressive reaction diffusion planner.<n>Our framework is validated in real-world applications, including virtual reality interface for human-robot interaction.
  arXiv  Detail & Related papers  (2025-08-04T06:35:48Z)
• The Coming Crisis of Multi-Agent Misalignment: AI Alignment Must Be a Dynamic and Social Process [13.959658276224266]
  AI alignment with human values and preferences remains a core challenge.<n>As agents engage with one another, they must coordinate to accomplish both individual and collective goals.<n>Social structure can deter or shatter group and individual values.<n>We call on the AI community to treat human, preferential, and objective alignment as an interdependent concept.
  arXiv  Detail & Related papers  (2025-06-01T16:39:43Z)
• Position: Towards Bidirectional Human-AI Alignment [109.57781720848669]
  We argue that the research community should explicitly define and critically reflect on "alignment" to account for the bidirectional and dynamic relationship between humans and AI.<n>We introduce the Bidirectional Human-AI Alignment framework, which not only incorporates traditional efforts to align AI with human values but also introduces the critical, underexplored dimension of aligning humans with AI.
  arXiv  Detail & Related papers  (2024-06-13T16:03:25Z)
• Towards interactive evaluations for interaction harms in human-AI systems [8.989911701384788]
  We propose a shift towards evaluation based on textitinteractional ethics, which focuses on textitinteraction harms<n>First, we discuss the limitations of current evaluation methods, which (1) are static, (2) assume a universal user experience, and (3) have limited construct validity.<n>We present practical principles for designing interactive evaluations. These include ecologically valid interaction scenarios, human impact metrics, and diverse human participation approaches.
  arXiv  Detail & Related papers  (2024-05-17T08:49:34Z)
• Human-AI Coevolution [48.74579595505374]
  Coevolution AI is a process in which humans and AI algorithms continuously influence each other. This paper introduces Coevolution AI as the cornerstone for a new field of study at the intersection between AI and complexity science.
  arXiv  Detail & Related papers  (2023-06-23T18:10:54Z)
• Training Socially Aligned Language Models on Simulated Social Interactions [99.39979111807388]
  Social alignment in AI systems aims to ensure that these models behave according to established societal values. Current language models (LMs) are trained to rigidly replicate their training corpus in isolation. This work presents a novel training paradigm that permits LMs to learn from simulated social interactions.
  arXiv  Detail & Related papers  (2023-05-26T14:17:36Z)

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.