mlsanityData to 14 Oct 2026

ADEPTS: A Capability Framework for Human-Centered Agent Design

arXiv 2507.15885 ↗First posted 18 Jul 2025cs.AI cs.HC cs.LGcited by 0

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

Large language models have paved the way to powerful and flexible AI agents, assisting humans by increasingly integrating into their daily life. This flexibility, potential, and growing adoption demands a holistic and cross-disciplinary approach to developing, monitoring and discussing the capabilities required for agent-driven user experiences. However, current guidance on human-centered AI agent development is scattered: UX heuristics focus on interface behaviors, engineering taxonomies describe internal pipelines, and ethics checklists address high-level governance. There is no concise, user-facing vocabulary that tells teams what an agent should fundamentally be able to do. We introduce ADEPTS, a capability framework defining a set of core user-facing capabilities to provide unified guidance around the development of AI agents. ADEPTS is based on six principles for human-centered agent design, that express the minimal, user-facing capabilities an AI agent should demonstrate to be understandable, controllable and trustworthy in everyday use. ADEPTS complements existing frameworks and taxonomies; differently from them, it sits at the interface between technical and experience development. By presenting ADEPTS, we aim to condense complex AI-UX requirements into a compact framework that is actionable guidance for AI researchers, designers, engineers, and policy reviewers alike. We believe ADEPTS has the potential of accelerating the improvement of user-relevant agent capabilities, of easing the design of experiences that take advantage of those capabilities, and of providing a shared language to track and discuss progress around the development of AI agents.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 17 of its 55 references that are in the map. First posted on arXiv 18 Jul 2025.

Builds on

17 of 55 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Survey on Evaluation of LLM-based Agents20 Mar

Other references · 16

  1. 2023Code Llama: Open Foundation Models for Codecited by 2,139
  2. 2016Concrete Problems in AI Safetycited by 1,642
  3. 2017Towards A Rigorous Science of Interpretable Machine Learningcited by 1,416
  4. 2025GR00T N1: An Open Foundation Model for Generalist Humanoid Robotscited by 1,225
  5. 2023Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversationscited by 1,207
  6. 2025UI-TARS: Pioneering Automated GUI Interaction with Native Agentscited by 610
  7. 2024Mechanistic Interpretability for AI Safety -- A Reviewcited by 422
  8. 2022Measuring Progress on Scalable Oversight for Large Language Modelscited by 225
  9. 2025Constitutional Classifiers: Defending against Universal Jailbreaks across Thousands of Hours of Red Teamingcited by 181
  10. 2024Large Language Model-Based Agents for Software Engineering: A Surveycited by 178
  11. 2025Measuring AI Ability to Complete Long Software Taskscited by 156
  12. 2025Deep Research Agents: A Systematic Examination And Roadmapcited by 128
4 more
  1. 2021Human-Centered Explainable AI (XAI): From Algorithms to User Experiencescited by 123
  2. 2025OS-Harm: A Benchmark for Measuring Safety of Computer Use Agentscited by 111
  3. 2025Superintelligent Agents Pose Catastrophic Risks: Can Scientist AI Offer a Safer Path?cited by 75
  4. 2024Generalist Virtual Agents: A Survey on Autonomous Agents Across Digital Platformscited by 13

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026A Framework of User Experience Principles for Human-AI Agent Interaction in the Workplace
  2. 2026Design Principles for Human-Agent Interaction
  3. 2025Designing The Internet of Agents: A Framework for Trustworthy, Transparent, and Collaborative Human-Agent Interaction (HAX)
  4. 2026Affora: A Design System for Agent-Friendly Interfaces
  5. 2026Human Tool: An MCP-Style Framework for Human-Agent Collaboration
  6. 2026From Human Interfaces to Agent Interfaces: Rethinking Software Design in the Age of AI-Native Systems
  7. 2025Understanding User Experiences of Computer Use Agents: Design Space and Opportunities for Building Agent UX Prototypes
  8. 2026From Human-Human Collaboration to Human-Agent Collaboration: A Vision, Design Philosophy, and an Empirical Framework for Achieving Successful Partnerships Between Humans and LLM Agents