CARD: Towards Conditional Design of Multi-agent Topological Structures

TL;DR

CARD (Conditional Agentic Graph Designer), a conditional graph-generation framework that instantiates AMACP, a protocol for adaptive multi-agent communication that explicitly incorporates dynamic environmental signals into graph construction, enabling topology adaptation at both training and runtime.

Abstract

Large language model (LLM)-based multi-agent systems have shown strong capabilities in tasks such as code generation and collaborative reasoning. However, the effectiveness and robustness of these systems critically depend on their communication topology, which is often fixed or statically learned, ignoring real-world dynamics such as model upgrades, API (or tool) changes, or knowledge source variability. To address this limitation, we propose CARD (Conditional Agentic Graph Designer), a conditional graph-generation framework that instantiates AMACP, a protocol for adaptive multi-agent communication. CARD explicitly incorporates dynamic environmental signals into graph construction, enabling topology adaptation at both training and runtime. Through a conditional variational graph encoder and environment-aware optimization, CARD produces communication structures that are both effective and resilient to shifts in model capability or resource availability. Empirical results on HumanEval, MATH, and MMLU demonstrate that CARD consistently outperforms static and prompt-based baselines, achieving higher accuracy and robustness across diverse conditions. The source code is available at: https://github.com/Warma10032/CARD.

Figures (8)

• Figure 1: Agent attributes and corresponding communication topologies under two environmental configurations, illustrating that topology is determined by both task requirements and the capabilities of the model base and available resources.
• Figure 2: Overview of the Conditional Agentic Graph Designer (CARD) framework. Agent profiles and dynamic environment conditions are encoded into embeddings, which a conditional graph-generation module (Encoder $\rightarrow$ Condition Adaptation $\rightarrow$ Decoder) uses to produce an adaptive communication topology. CARD then performs environment-aware training, iteratively refining graphs under changing resource configurations, and deploys runtime adaptation to automatically update the multi-agent topology in response to new environmental states.
• Figure 3: Performance and gains of w/o Cond., w/ Cond.p, and CARD on HumanEval, MATH, and MMLU across LLM bases (M1–M5, same to Table \ref{['tab:main']}). Top: absolute accuracy (%). Bottom:$\Delta$ accuracy (%) over the w/o Cond. baseline.
• Figure 4: Visualization of CARD topology matrices (See Appendix \ref{['apd:sdata']} for matrices and correlation analysis details.) under different conditions. Edge thickness reflects the communication probability between agents. Configurations 1 to 4 (Table \ref{['tab:MMLU config with search']}) are shown from left to right.
• Figure 5: Left: Accuracy on MATH and HumanEval across LLMs with different reasoning capabilities. Right: Accuracy across different model sizes within the same LLM family.