A Measure Based Generalizable Approach to Understandability

• URL: http://arxiv.org/abs/2503.21615v2
• Date: Wed, 23 Apr 2025 17:39:20 GMT
• Title: A Measure Based Generalizable Approach to Understandability
• Authors: Vikas Kushwaha, Sruti Srinivasa Ragavan, Subhajit Roy,
• Abstract summary: Successful agent-human partnerships require that any agent generated information is understandable to the human.<n>This paper argues for developing domain-agnostic measures of understandability that can be used as directives for state-of-the-art agents.
• Score: 4.288076913047139
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Successful agent-human partnerships require that any agent generated information is understandable to the human, and that the human can easily steer the agent towards a goal. Such effective communication requires the agent to develop a finer-level notion of what is understandable to the human. State-of-the-art agents, including LLMs, lack this detailed notion of understandability because they only capture average human sensibilities from the training data, and therefore afford limited steerability (e.g., requiring non-trivial prompt engineering). In this paper, instead of only relying on data, we argue for developing generalizable, domain-agnostic measures of understandability that can be used as directives for these agents. Existing research on understandability measures is fragmented, we survey various such efforts across domains, and lay a cognitive-science-rooted groundwork for more coherent and domain-agnostic research investigations in future.

Related papers

• A Survey of AI Agent Protocols [35.431057321412354]
  There is no standard way for large language models (LLMs) agents to communicate with external tools or data sources. This lack of standardized protocols makes it difficult for agents to work together or scale effectively. A unified communication protocol for LLM agents could change this.
  arXiv  Detail & Related papers  (2025-04-23T14:07:26Z)
• Generating Causal Explanations of Vehicular Agent Behavioural Interactions with Learnt Reward Profiles [13.450023647228843]
  We learn a weighting of reward metrics for agents such that explanations for agent interactions can be causally inferred.<n>We validate our approach quantitatively and qualitatively across three real-world driving datasets.
  arXiv  Detail & Related papers  (2025-03-18T01:53:59Z)
• VeriLA: A Human-Centered Evaluation Framework for Interpretable Verification of LLM Agent Failures [3.075266204492352]
  Large language model (LLM) agents in compound AI systems often fail to meet human standards, leading to errors that compromise the system's overall performance.<n>This paper introduces a human-centered evaluation framework for verifying LLM Agent failures (VeriLA)<n>VeriLA systematically assesses agent failures to reduce human effort and make these agent failures interpretable to humans.
  arXiv  Detail & Related papers  (2025-03-16T21:11:18Z)
• AgentDAM: Privacy Leakage Evaluation for Autonomous Web Agents [75.85554113398626]
  We develop a benchmark called AgentDAM to evaluate how well existing and future AI agents can limit processing of potentially private information.<n>Our benchmark simulates realistic web interaction scenarios and is adaptable to all existing web navigation agents.
  arXiv  Detail & Related papers  (2025-03-12T19:30:31Z)
• Challenges in Human-Agent Communication [55.53932430345333]
  We identify and analyze twelve key communication challenges that these systems pose.<n>These include challenges in conveying information from the agent to the user, challenges in enabling the user to convey information to the agent, and overarching challenges that need to be considered across all human-agent communication.<n>Our findings serve as an urgent call for new design patterns, principles, and guidelines to support transparency and control in these systems.
  arXiv  Detail & Related papers  (2024-11-28T01:21:26Z)
• Large Language Model-based Human-Agent Collaboration for Complex Task Solving [94.3914058341565]
  We introduce the problem of Large Language Models (LLMs)-based human-agent collaboration for complex task-solving. We propose a Reinforcement Learning-based Human-Agent Collaboration method, ReHAC. This approach includes a policy model designed to determine the most opportune stages for human intervention within the task-solving process.
  arXiv  Detail & Related papers  (2024-02-20T11:03:36Z)
• Tell Me More! Towards Implicit User Intention Understanding of Language Model Driven Agents [110.25679611755962]
  Current language model-driven agents often lack mechanisms for effective user participation, which is crucial given the vagueness commonly found in user instructions. We introduce Intention-in-Interaction (IN3), a novel benchmark designed to inspect users' implicit intentions through explicit queries. We empirically train Mistral-Interact, a powerful model that proactively assesses task vagueness, inquires user intentions, and refines them into actionable goals.
  arXiv  Detail & Related papers  (2024-02-14T14:36:30Z)
• Reinforcement Learning Interventions on Boundedly Rational Human Agents in Frictionful Tasks [25.507656595628376]
  We introduce a framework in which an AI agent intervenes on the parameters of a Markov Decision Process (MDP) belonging to a boundedly rational human agent. We show that AI planning with our human models can lead to helpful policies on a wide range of more complex, ground-truth humans.
  arXiv  Detail & Related papers  (2024-01-26T14:59:48Z)
• The Rise and Potential of Large Language Model Based Agents: A Survey [91.71061158000953]
  Large language models (LLMs) are regarded as potential sparks for Artificial General Intelligence (AGI) We start by tracing the concept of agents from its philosophical origins to its development in AI, and explain why LLMs are suitable foundations for agents. We explore the extensive applications of LLM-based agents in three aspects: single-agent scenarios, multi-agent scenarios, and human-agent cooperation.
  arXiv  Detail & Related papers  (2023-09-14T17:12:03Z)
• A Cognitive Framework for Delegation Between Error-Prone AI and Human Agents [0.0]
  We investigate the use of cognitively inspired models of behavior to predict the behavior of both human and AI agents. The predicted behavior is used to delegate control between humans and AI agents through the use of an intermediary entity.
  arXiv  Detail & Related papers  (2022-04-06T15:15:21Z)
• Modeling Bounded Rationality in Multi-Agent Simulations Using Rationally Inattentive Reinforcement Learning [85.86440477005523]
  We study more human-like RL agents which incorporate an established model of human-irrationality, the Rational Inattention (RI) model. RIRL models the cost of cognitive information processing using mutual information. We show that using RIRL yields a rich spectrum of new equilibrium behaviors that differ from those found under rational assumptions.
  arXiv  Detail & Related papers  (2022-01-18T20:54:00Z)
• Building Affordance Relations for Robotic Agents - A Review [7.50722199393581]
  Affordances describe the possibilities for an agent to perform actions with an object. We review and find common ground amongst different strategies that use the concept of affordances within robotic tasks. We identify and discuss a range of interesting research directions involving affordances that have the potential to improve the capabilities of an AI agent.
  arXiv  Detail & Related papers  (2021-05-14T08:35:18Z)

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.