Narrowing Action Choices with AI Improves Human Sequential Decisions

• URL: http://arxiv.org/abs/2510.16097v1
• Date: Fri, 17 Oct 2025 18:00:00 GMT
• Title: Narrowing Action Choices with AI Improves Human Sequential Decisions
• Authors: Eleni Straitouri, Stratis Tsirtsis, Ander Artola Velasco, Manuel Gomez-Rodriguez,
• Abstract summary: Recent work has shown that it is possible to design decision support systems that do not require human experts to understand.<n>We develop a system that uses an AI to narrow down the set of actions a human can take and then asks the human to take an action from this action set.<n>We find that participants who play the game supported by our system outperform those who play on their own by $$30$% and the AI agent used by our system by $$$2$%.
• Score: 15.988574580713328
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Recent work has shown that, in classification tasks, it is possible to design decision support systems that do not require human experts to understand when to cede agency to a classifier or when to exercise their own agency to achieve complementarity$\unicode{x2014}$experts using these systems make more accurate predictions than those made by the experts or the classifier alone. The key principle underpinning these systems reduces to adaptively controlling the level of human agency, by design. Can we use the same principle to achieve complementarity in sequential decision making tasks? In this paper, we answer this question affirmatively. We develop a decision support system that uses a pre-trained AI agent to narrow down the set of actions a human can take to a subset, and then asks the human to take an action from this action set. Along the way, we also introduce a bandit algorithm that leverages the smoothness properties of the action sets provided by our system to efficiently optimize the level of human agency. To evaluate our decision support system, we conduct a large-scale human subject study ($n = 1{,}600$) where participants play a wildfire mitigation game. We find that participants who play the game supported by our system outperform those who play on their own by $\sim$$30$% and the AI agent used by our system by $>$$2$%, even though the AI agent largely outperforms participants playing without support. We have made available the data gathered in our human subject study as well as an open source implementation of our system at https://github.com/Networks-Learning/narrowing-action-choices .

Related papers

• Training LLM Agents to Empower Humans [67.80021254324294]
  We propose a new approach to tuning assistive language models based on maximizing the human's empowerment.<n>Our empowerment-maximizing method, Empower, only requires offline text data.<n>We show that agents trained with Empower increase the success rate of a simulated human programmer on challenging coding questions by an average of 192%.
  arXiv  Detail & Related papers  (2025-10-15T16:09:33Z)
• HumanAgencyBench: Scalable Evaluation of Human Agency Support in AI Assistants [5.4831302830611195]
  We develop the idea of human agency by integrating philosophical and scientific theories of agency with AI-assisted evaluation methods.<n>We develop HumanBench (HAB), a scalable and adaptive benchmark with six dimensions of human agency based on typical AI use cases.
  arXiv  Detail & Related papers  (2025-09-10T11:10:10Z)
• Towards Human-AI Complementarity in Matching Tasks [18.703064369029022]
  We propose a data-driven algorithmic matching system that takes a collaborative approach.<n>Comatch selects only the decisions that it is the most confident in, deferring the rest to the human decision maker.<n>The results demonstrate that the matching outcomes produced by comatch outperform those generated by either human participants or by algorithmic matching on their own.
  arXiv  Detail & Related papers  (2025-08-18T18:02:45Z)
• Human aversion? Do AI Agents Judge Identity More Harshly Than Performance [0.06554326244334868]
  We investigate how AI agents based on large language models assess and integrate human input.<n>We find that the AI system systematically discounts human advice, penalizing human errors more severely than algorithmic errors.
  arXiv  Detail & Related papers  (2025-03-31T02:05:27Z)
• Combining AI Control Systems and Human Decision Support via Robustness and Criticality [53.10194953873209]
  We extend a methodology for adversarial explanations (AE) to state-of-the-art reinforcement learning frameworks. We show that the learned AI control system demonstrates robustness against adversarial tampering. In a training / learning framework, this technology can improve both the AI's decisions and explanations through human interaction.
  arXiv  Detail & Related papers  (2024-07-03T15:38:57Z)
• Mixed-Initiative Human-Robot Teaming under Suboptimality with Online Bayesian Adaptation [0.6591036379613505]
  We develop computational modeling and optimization techniques for enhancing the performance of suboptimal human-agent teams. We adopt an online Bayesian approach that enables a robot to infer people's willingness to comply with its assistance in a sequential decision-making game. Our user studies show that user preferences and team performance indeed vary with robot intervention styles.
  arXiv  Detail & Related papers  (2024-03-24T14:38:18Z)
• REBEL: Reward Regularization-Based Approach for Robotic Reinforcement Learning from Human Feedback [61.54791065013767]
  A misalignment between the reward function and human preferences can lead to catastrophic outcomes in the real world.<n>Recent methods aim to mitigate misalignment by learning reward functions from human preferences.<n>We propose a novel concept of reward regularization within the robotic RLHF framework.
  arXiv  Detail & Related papers  (2023-12-22T04:56:37Z)
• The MineRL BASALT Competition on Learning from Human Feedback [58.17897225617566]
  The MineRL BASALT competition aims to spur forward research on this important class of techniques. We design a suite of four tasks in Minecraft for which we expect it will be hard to write down hardcoded reward functions. We provide a dataset of human demonstrations on each of the four tasks, as well as an imitation learning baseline.
  arXiv  Detail & Related papers  (2021-07-05T12:18:17Z)
• Multi-Principal Assistance Games [11.85513759444069]
  Impossibility theorems in social choice theory and voting theory can be applied to such games. We analyze in particular a bandit apprentice game in which the humans act first to demonstrate their individual preferences for the arms. We propose a social choice method that uses shared control of a system to combine preference inference with social welfare optimization.
  arXiv  Detail & Related papers  (2020-07-19T00:23:25Z)
• Is the Most Accurate AI the Best Teammate? Optimizing AI for Teamwork [54.309495231017344]
  We argue that AI systems should be trained in a human-centered manner, directly optimized for team performance. We study this proposal for a specific type of human-AI teaming, where the human overseer chooses to either accept the AI recommendation or solve the task themselves. Our experiments with linear and non-linear models on real-world, high-stakes datasets show that the most accuracy AI may not lead to highest team performance.
  arXiv  Detail & Related papers  (2020-04-27T19:06:28Z)
• A Case for Humans-in-the-Loop: Decisions in the Presence of Erroneous Algorithmic Scores [85.12096045419686]
  We study the adoption of an algorithmic tool used to assist child maltreatment hotline screening decisions. We first show that humans do alter their behavior when the tool is deployed. We show that humans are less likely to adhere to the machine's recommendation when the score displayed is an incorrect estimate of risk.
  arXiv  Detail & Related papers  (2020-02-19T07:27:32Z)

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.