This episode of Techsplainers explores two fundamental capabilities of AI agents: communication and learning. We examine how AI agents exchange information with each other and humans, including agent-to-agent protocols like KQML and FIPA-ACL. We also look at the challenges they face with standardization, ambiguity, latency, and security. The discussion then shifts to how agents learn and improve over time, covering supervised learning with labeled data, unsupervised learning that finds patterns without human oversight, and reinforcement learning through trial and error with rewards. We also explore continuous learning, where agents adapt to new information without forgetting previous knowledge, and how these capabilities combine in multi-agent systems to create collaborative intelligence that can solve complex problems across various industries. Find more information at <a href="https://www.ibm.com/think/podcasts/techsplainers" rel="noopener noreferrer" target="_blank">https://www.ibm.com/think/podcasts/techsplainers</a>. Narrated by Selma Pacheco Jimenez

This episode of Techsplainers explores how AI agents communicate and learn—from agent protocols to supervised, unsupervised, and reinforcement learning techniques that power intelligent systems.

What is AI agent communication and AI agent learning?

This episode of Techsplainers explores the concept of tool calling in artificial intelligence, explaining how it enables AI models to interact with external tools, APIs, and systems beyond their native capabilities. We walk through how tool calling works, from recognizing when external assistance is needed to selecting appropriate tools and processing responses. The episode highlights the powerful combination of tool calling with retrieval augmented generation (RAG) and examines real-world applications in information retrieval, code execution, process automation, IoT device control, and personalized recommendations. By bridging the gap between AI reasoning and action, tool calling is transforming passive AI assistants into proactive digital agents capable of completing complex, multi-step tasks through dynamic access to external resources. Find more information at <a href="https://www.ibm.com/think/podcasts/techsplainers" rel="noopener noreferrer" target="_blank">https://www.ibm.com/think/podcasts/techsplainers</a>. Narrated by Selma Pacheco Jimenez

This episode of Techsplainers explores tool calling—how AI models interact with external tools and APIs to perform complex tasks beyond their training data, transforming them from passive assistants into proactive agents. 

What is tool calling?

This episode of Techsplainers explores the crucial components of AI agent memory and agentic reasoning. We delve into how AI agents store and recall information through different memory types—including short-term, long-term, episodic, semantic, and procedural memory—and how frameworks like LangChain and LangGraph implement these capabilities. The episode also examines various reasoning paradigms that power AI decision-making, from simple conditional logic to sophisticated approaches like ReAct, ReWOO, and multiagent reasoning. By understanding these complementary components, listeners gain insight into how modern AI systems transform from passive models into intelligent agents that can maintain context across interactions, learn from past experiences, and make autonomous decisions to achieve complex goals. Find more information at <a href="https://www.ibm.com/think/podcasts/techsplainers" rel="noopener noreferrer" target="_blank">https://www.ibm.com/think/podcasts/techsplainers</a>. Narrated by Selma Pacheco Jimenez

This episode of Techsplainers explores AI agent memory and reasoning—how intelligent systems store experiences and make decisions, transforming passive AI into autonomous problem-solving agents. 

What is AI agent memory and agentic reasoning?

What is Ai agent memory and agentic reasoning?

This episode of Techsplainers explores two fundamental capabilities of AI agents: perception and planning. We examine how agents perceive their environment through visual, auditory, textual, environmental, and predictive means, breaking down the four-step perception process from sensory input collection to decision-making. The discussion then shifts to how agents use this perceived information to plan their actions, covering goal definition, state representation, action sequencing, and optimization techniques like heuristic search and reinforcement learning. We also explore how different planning frameworks operate and how planning becomes more complex in multi-agent systems where coordination is essential. By understanding these interconnected components, listeners gain insight into what makes AI agents truly intelligent and capable of operating autonomously in complex environments. Find more information at <a href="https://www.ibm.com/think/podcasts/techsplainers" rel="noopener noreferrer" target="_blank">https://www.ibm.com/think/podcasts/techsplainers</a>. Narrated by Selma Pacheco Jimenez

This episode of Techsplainers explores how AI agents perceive their world and plan their actions—from visual and auditory perception to goal-setting and optimization techniques. 

What is AI agent perception and AI agent planning?

This episode of Techsplainers explores the essential components that make AI agents function, breaking down the "brain" of these intelligent systems. We examine how perception enables agents to understand their environment through various inputs, while planning allows them to map out complex task sequences. The discussion covers memory systems that provide both short-term context and long-term learning, reasoning modules that power decision-making, and action capabilities that execute tasks through tool calling. We also investigate how communication facilitates interaction with humans and other agents and how learning capabilities enable continuous improvement over time. By understanding these interconnected components, listeners gain insight into how AI agents operate across various industries and applications. Find more information at <a href="https://www.ibm.com/think/podcasts/techsplainers" rel="noopener noreferrer" target="_blank">https://www.ibm.com/think/podcasts/techsplainers</a>. Narrated by Selma Pacheco Jimenez

This episode of Techsplainers explores AI agent components: perception, planning, memory, reasoning, action, communication, and learning. These are the building blocks of intelligent autonomous systems.

What are the components of AI agents?

This episode of Techsplainers explores reinforcement learning, a machine learning approach where AI agents learn to make decisions through trial and error by interacting with their environment. Unlike supervised learning's labeled data or unsupervised learning's pattern discovery, reinforcement learning teaches through reward signals—similar to how we might train a pet with treats. The episode breaks down the core components of this approach, including the Markov decision process framework, the critical exploration-exploitation tradeoff, and key elements like policy, reward signals, and value functions. We also examine major reinforcement learning methods, such as dynamic programming, Monte Carlo techniques, and temporal difference learning. The discussion covers real-world applications in robotics and natural language processing, highlighting both impressive successes like AlphaGo and ongoing challenges in creating effective learning environments with meaningful reward systems. Find more information at <a href="https://www.ibm.com/think/podcasts/techsplainers" rel="noopener noreferrer" target="_blank">https://www.ibm.com/think/podcasts/techsplainers</a>. Narrated by Anna Gutowska

This episode of Techsplainers explores reinforcement learning—how AI agents learn through trial and error by receiving rewards for good decisions, similar to training a pet. 

What is reinforcement learning?

This episode of Techsplainers explores semi-supervised learning, the machine learning approach that bridges supervised and unsupervised techniques by combining small amounts of labeled data with larger volumes of unlabeled information. The episode explains why this method is crucial when obtaining fully labeled datasets is prohibitively expensive or time-consuming, such as in medical imaging or genetic analysis. We break down the key assumptions that make semi-supervised learning work—including the cluster assumption, smoothness assumption, low-density assumption, and manifold assumption—and how they help models generalize beyond limited labeled examples. The discussion covers major implementation approaches, including transductive methods like label propagation, and inductive methods like wrapper techniques, unsupervised pre-processing, and intrinsically semi-supervised algorithms. Real-world applications and challenges are also examined, providing listeners with a comprehensive understanding of this practical machine learning technique. Find more information at <a href="https://www.ibm.com/think/podcasts/techsplainers" rel="noopener noreferrer" target="_blank">https://www.ibm.com/think/podcasts/techsplainers</a>. Narrated by Anna Gutowska&nbsp;

This episode of Techsplainers explores semi-supervised learning—how AI combines small amounts of labeled data with unlabeled information to train effective models when labeling is scarce. 

What is semi-supervised learning?

Introducing the Techsplainers by IBM podcast, your new podcast for quick, powerful takes on today’s most important AI and tech topics. Each episode brings you bite-sized learning designed to fit your day, whether you’re driving, exercising, or just curious for something new. This is just the beginning. Tune in every weekday at 6 AM ET for fresh insights, new voices, and smarter learning.

What is AI agent communication and AI agent learning?

DESCRIPTION

Recent Episodes

What is AI agent communication and AI agent learning?

DESCRIPTION

Related Resources

Recent Episodes

What is tool calling?

What is AI agent memory and agentic reasoning?

What is AI agent perception and AI agent planning?

What are the components of AI agents?

What is reinforcement learning?

What is semi-supervised learning?