Search papers, labs, and topics across Lattice.
This paper introduces E2-Explainer, a model-agnostic framework that enhances the interpretability of communication topologies in LLM-based multi-agent systems by framing topology explanation as a causal attribution problem. By employing a Granger-style objective, the method identifies critical communication subgraphs that are essential for task preservation, allowing for efficient pruning of redundant communication edges. Experimental results show that E2-Explainer not only provides insights into effective communication structures but also significantly reduces communication costs while maintaining competitive performance across various benchmarks.
E2-Explainer reveals the hidden communication subgraphs that drive successful collaboration in LLM-based multi-agent systems, enabling both interpretability and cost efficiency.
The performance of large language model (LLM)-based multi-agent systems (MAS) largely depends on effective communication topologies. Existing topology generation methods, however, typically learn communication topologies through black-box optimization driven solely by task-level rewards. While effective, such optimization provides little insight into why particular communication edges are selected, making it difficult to identify the critical communication subgraphs responsible for successful collaboration. To address this limitation, we propose E2-Explainer, a model-agnostic framework for providing interpretable explanations of communication topologies produced by arbitrary topology generators. Specifically, we formulate topology explanation as a causal attribution problem that identifies compact communication subgraphs supported by edge-level evidence of task preservation. We obtain this evidence with a Granger-style objective that measures how masking each communication channel changes the task outcome and the stability of the final response. The resulting budgeted subgraphs are then distilled into an amortized explainer, enabling efficient post-hoc explanation without repeated edge-level evaluations at deployment. Extensive experiments on multiple reasoning and coding benchmarks demonstrate that E2-Explainer identifies critical communication subgraphs that preserve successful collaboration. These subgraphs can also be executed directly to prune redundant communication edges, substantially reducing communication costs while maintaining competitive task performance.
