DIG to Heal: Scaling General-purpose Agent Collaboration via Explainable Dynamic Decision Paths

TL;DR

This paper introduces the Dynamic Interaction Graph (DIG), a novel method to observe, explain, and correct emergent collaboration among general-purpose LLM agents operating without predefined roles, enhancing understanding of multi-agent problem-solving.

Contribution

The paper presents DIG, a new framework for capturing and analyzing emergent multi-agent collaboration as a causal network, enabling real-time interpretability and error correction.

Findings

DIG effectively visualizes emergent collaboration paths.

DIG allows real-time detection of collaboration-induced errors.

DIG enhances understanding of multi-agent problem-solving dynamics.

Abstract

The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-purpose large language model (LLM) agents to collaboratively complete complex tasks. While many agentic AI systems utilize predefined workflows or agent roles in order to reduce complexity, ideally these agents would be truly autonomous, able to achieve emergent collaboration even as the number of collaborating agents increases. Yet in practice, such unstructured interactions can lead to redundant work and cascading failures that are difficult to interpret or correct. In this work, we study multi-agent systems composed of general-purpose LLM agents that operate without predefined roles, control flow, or communication constraints, relying instead on emergent collaboration to solve problems. We introduce the Dynamic Interaction Graph (DIG), which captures emergent collaboration as a time-evolving causal network of agent activations and interactions. DIG makes emergent collaboration observable and explainable for the first time, enabling real-time identification, explanation, and correction of collaboration-induced error patterns directly from agents' collaboration paths. Thus, DIG fills a critical gap in understanding how general LLM agents solve problems together in truly agentic multi-agent systems. The project webpage can be found at: https://happyeureka.github.io/dig.