From Features to Actions: Explainability in Traditional and Agentic AI Systems
#Explainable AI #Agentic AI #Large Language Models #Machine Learning #Sequential Decision Making #arXiv #Interpretability
📌 Key Takeaways
- Traditional XAI methods focusing on single-point predictions are becoming obsolete for agentic systems.
- Agentic AI behavior is defined by multi-step trajectories rather than one-off input/output relationships.
- The rise of Large Language Models has enabled autonomous agents that require new forms of behavioral transparency.
- Future explainability frameworks must account for sequential decision-making to ensure safety and accountability.
📖 Full Retelling
🏷️ Themes
Artificial Intelligence, Explainability, Technology Trends
📚 Related People & Topics
Machine learning
Study of algorithms that improve automatically through experience
Machine learning (ML) is a field of study in artificial intelligence concerned with the development and study of statistical algorithms that can learn from data and generalize to unseen data, and thus perform tasks without explicit instructions. Within a subdiscipline in machine learning, advances i...
Large language model
Type of machine learning model
A large language model (LLM) is a language model trained with self-supervised machine learning on a vast amount of text, designed for natural language processing tasks, especially language generation. The largest and most capable LLMs are generative pre-trained transformers (GPTs) that provide the c...
Explainable artificial intelligence
AI whose outputs can be understood by humans
Within artificial intelligence (AI), explainable AI (XAI), generally overlapping with interpretable AI or explainable machine learning (XML), is a field of research that explores methods that provide humans with the ability of intellectual oversight over AI algorithms. The main focus is on the reaso...
AI agent
Systems that perform tasks without human intervention
In the context of generative artificial intelligence, AI agents (also referred to as compound AI systems or agentic AI) are a class of intelligent agents distinguished by their ability to operate autonomously in complex environments. Agentic AI tools prioritize decision-making over content creation ...
🔗 Entity Intersection Graph
Connections for Machine learning:
- 🌐 Large language model (6 shared articles)
- 🌐 Generative artificial intelligence (3 shared articles)
- 🌐 Electroencephalography (3 shared articles)
- 🌐 Computer vision (3 shared articles)
- 🌐 Natural language processing (2 shared articles)
- 🌐 Artificial intelligence (2 shared articles)
- 🌐 Graph neural network (2 shared articles)
- 🌐 Neural network (2 shared articles)
- 🌐 Transformer (1 shared articles)
- 🌐 User interface (1 shared articles)
- 👤 Stuart Russell (1 shared articles)
- 🌐 Ethics of artificial intelligence (1 shared articles)
📄 Original Source Content
arXiv:2602.06841v1 Announce Type: new Abstract: Over the last decade, explainable AI has primarily focused on interpreting individual model predictions, producing post-hoc explanations that relate inputs to outputs under a fixed decision structure. Recent advances in large language models (LLMs) have enabled agentic AI systems whose behaviour unfolds over multi-step trajectories. In these settings, success and failure are determined by sequences of decisions rather than a single output. While u