中文
相关论文

相关论文: Beyond the Black Box: Interpretability of Agentic …

200 篇论文

Machine learning has shown successes for complex learning problems in which data/parameters can be multidimensional and too complex for a first-principles based analysis. Some applications that utilize machine learning require human…

机器学习 · 计算机科学 2020-09-14 Nutta Homdee , John Lach

Machine learning is frequently used in affective computing, but presents challenges due the opacity of state-of-the-art machine learning methods. Because of the impact affective machine learning systems may have on an individual's life, it…

机器学习 · 计算机科学 2025-10-07 David S. Johnson , Olya Hakobyan , Hanna Drimalla

One of the several obstacles in the widespread use of AI systems is the lack of requirements of interpretability that can enable a layperson to ensure the safe and reliable behavior of such systems. We extend the analysis of an agent…

人工智能 · 计算机科学 2021-08-24 Pulkit Verma , Siddharth Srivastava

Current agentic AI benchmarks predominantly evaluate task completion accuracy, while overlooking critical enterprise requirements such as cost-efficiency, reliability, and operational stability. Through systematic analysis of 12 main…

人工智能 · 计算机科学 2025-11-19 Sushant Mehta

Authorizing Large Language Model (LLM)-driven agents to dynamically invoke tools and access protected resources introduces significant security risks, and the risks grow dramatically as agents engage in multi-turn conversations and scale…

人工智能 · 计算机科学 2026-05-05 Majed El Helou , Benjamin Ryder , Chiara Troiani , Jean Diaconu , Hervé Muyal , Marcelo Yannuzzi

As we deploy autonomous agents in safety-critical domains, it becomes important to develop an understanding of their internal mechanisms and representations. We outline an approach to imitation learning for reverse-engineering black box…

人工智能 · 计算机科学 2020-06-23 Tom Bewley , Jonathan Lawry , Arthur Richards

Recent advances in agentic AI have shifted the focus from standalone Large Language Models (LLMs) to integrated systems that combine LLMs with tools, memory, and other agents to perform complex tasks. These multi-agent architectures enable…

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under differing assumptions, thus precluding the possibility of…

人工智能 · 计算机科学 2021-04-23 Sarath Sreedharan , Anagha Kulkarni , David E. Smith , Subbarao Kambhampati

As machine learning systems become more powerful they also become increasingly unpredictable and opaque. Yet, finding human-understandable explanations of how they work is essential for their safe deployment. This technical report…

The endowment of AI with reasoning capabilities and some degree of agency is widely viewed as a path toward more capable and generalizable systems. Our position is that the current development of agentic AI requires a more holistic,…

To benefit from AI advances, users and operators of AI systems must have reason to trust it. Trust arises from multiple interactions, where predictable and desirable behavior is reinforced over time. Providing the system's users with some…

人工智能 · 计算机科学 2022-01-27 Stephanie Galaitsi , Benjamin D. Trump , Jeffrey M. Keisler , Igor Linkov , Alexander Kott

Cooperative multi-agent reinforcement learning (MARL) has made substantial strides in addressing the distributed decision-making challenges. However, as multi-agent systems grow in complexity, gaining a comprehensive understanding of their…

人工智能 · 计算机科学 2023-12-15 Wiem Khlifi , Siddarth Singh , Omayma Mahjoub , Ruan de Kock , Abidine Vall , Rihab Gorsane , Arnu Pretorius

Autonomous agents powered by Large Language Models are transforming AI, creating an imperative for the visualization field to embrace agentic frameworks. However, our field's focus on a human in the sensemaking loop raises critical…

人机交互 · 计算机科学 2025-09-17 Vaishali Dhanoa , Anton Wolter , Gabriela Molina León , Hans-Jörg Schulz , Niklas Elmqvist

Artificial Intelligence algorithms have now become pervasive in multiple high-stakes domains. However, their internal logic can be obscure to humans. Explainable Artificial Intelligence aims to design tools and techniques to illustrate the…

人机交互 · 计算机科学 2024-04-29 Eleonora Cappuccio , Daniele Fadda , Rosa Lanzilotti , Salvatore Rinzivillo

AI agents increasingly act through external tools: they query databases, execute shell commands, read and write files, and send network requests. Yet in most current agent stacks, model-generated tool calls are handed to the execution layer…

密码学与安全 · 计算机科学 2026-03-16 Aojie Yuan , Zhiyuan Su , Yue Zhao

Multi-agent systems powered by large language models (LLMs) are transforming enterprise automation, yet systematic evaluation methodologies for assessing tool-use reliability remain underdeveloped. We introduce a comprehensive diagnostic…

人工智能 · 计算机科学 2026-01-26 Donghao Huang , Gauri Malwe , Zhaoxia Wang

Evaluation is no longer a final checkpoint in the machine learning lifecycle. As AI systems evolve from static models to compound, tool-using agents, evaluation becomes a core control function. The question is no longer "How good is the…

计算与语言 · 计算机科学 2026-02-23 Ali El Filali , Inès Bedar

Causal machine learning tools are beginning to see use in real-world policy evaluation tasks to flexibly estimate treatment effects. One issue with these methods is that the machine learning models used are generally black boxes, i.e.,…

机器学习 · 计算机科学 2024-04-01 Patrick Rehill , Nicholas Biddle

As AI agents transition from research prototypes to enterprise production systems, the tool interfaces they consume remain rooted in human-oriented CRUD paradigms. This paper identifies five fundamental architectural mismatches between…

人工智能 · 计算机科学 2026-05-12 Kai Pan

Brought into the public discourse through investigative work by journalists and scholars, awareness of algorithmic harms is at an all-time high. An increasing amount of research has been conducted under the banner of enhancing responsible…

计算机与社会 · 计算机科学 2020-12-02 Josephine Seah