IACT: A Self-Organizing Recursive Model for General AI Agents: A Technical White Paper on the Architecture Behind kragent.ai

TL;DR

This paper presents IACT, a recursive, self-organizing model for general AI agents that dynamically adapts its structure through dialogue-driven interactions, enabling scalable, error-resilient autonomous workflows.

Contribution

It introduces a novel recursive architecture for autonomous agents that grow and adapt their topology based on user dialogue, improving flexibility and error handling.

Findings

Demonstrated in real-world workflows on kragent.ai

Enables scalable and adaptive agent organization

Uses bidirectional dialogues for error correction

Abstract

This technical white paper introduces the Interactive Agents Call Tree (IACT), a computational model designed to address the limitations of static, hard-coded agent workflows. Unlike traditional systems that require pre-defined graphs or specialized programming, IACT operates as a general-purpose autonomous system driven purely by user dialogue. Given a high-level objective, the system autonomously grows a dynamic, recursive agent topology incrementally tailored to the problem's structure. This allows it to scale its organizational complexity to match open-ended tasks. To mitigate the error propagation inherent in unidirectional function calls, IACT introduces interactional redundancy by replacing rigid invocations with bidirectional, stateful dialogues. This mechanism enables runtime error correction and ambiguity resolution. We describe the architecture, design principles, and practical lessons behind the production deployment of this model in the kragent.ai system, presenting qualitative evidence from real-world workflows rather than exhaustive benchmark results.