This article explores how tool calling enables AI agents to move beyond simple text generation by interacting with external systems. It explains the process where large language models generate structured data, such as JSON, instead of natural language to trigger specific functions and APIs.
- The mechanics of function definition within model prompts
- How reasoning leads a model to select appropriate tools for a task
- The transition from conversational responses to actionable command outputs
- The execution loop required for autonomous agent behavior
- The mechanics of function definition within model prompts
- How reasoning leads a model to select appropriate tools for a task
- The transition from conversational responses to actionable command outputs
- The execution loop required for autonomous agent behavior
This article explores the critical architectural decision of where to store conversation history when building AI agents. It examines how different storage strategies impact user experience, privacy, cost, and portability. The author compares service-managed versus client-managed storage models and details how modern APIs support both linear threads and forking/branching capabilities.
Key topics include:
* Service-Managed vs. Client-Managed storage tradeoffs
* Linear (single-threaded) vs. Forking-capable conversation models
* Strategies for context window management and compaction such as truncation, summarization, and sliding windows
* How Microsoft Agent Framework abstracts these patterns using AgentSession and ChatHistoryProvider to ensure provider-agnostic code
* Practical implementation examples for the Responses API in different modes
Key topics include:
* Service-Managed vs. Client-Managed storage tradeoffs
* Linear (single-threaded) vs. Forking-capable conversation models
* Strategies for context window management and compaction such as truncation, summarization, and sliding windows
* How Microsoft Agent Framework abstracts these patterns using AgentSession and ChatHistoryProvider to ensure provider-agnostic code
* Practical implementation examples for the Responses API in different modes
This position paper addresses the growing memory demands of multi-agent systems powered by large language models (LLMs). It frames multi-agent memory as a computer architecture problem, drawing parallels to traditional computer systems where memory hierarchy and bandwidth are critical bottlenecks. The authors distinguish between shared and distributed memory paradigms for agents and propose a three-layer memory hierarchy – I/O, cache, and memory – tailored for agentic systems. Key challenges identified include the need for protocols for cache sharing and memory access, and, crucially, establishing multi-agent memory consistency to ensure coherent and reliable operation.
OpenClaw is an open-source project that allows users to build and control AI agents. It provides a gateway for building agents and can be integrated with messaging apps such as Telegram. The article details the setup process, capabilities, and potential risks of using OpenClaw.
OpenClaw utilizes "skills" (packages of tools and instructions) and a "SOUL.md" file to define the agent's behavior and personality. The agent stores conversation history to improve its responses over time.
OpenClaw utilizes "skills" (packages of tools and instructions) and a "SOUL.md" file to define the agent's behavior and personality. The agent stores conversation history to improve its responses over time.
