aiqbench analysis
This research introduces E2-Explainer, a causal inference framework designed to interpret communication topologies in LLM-based multi-agent systems by identifying critical subgraphs responsible for task success. By quantifying the impact of masking specific channels on response stability and outcome preservation, the method enables efficient pruning of redundant edges without sacrificing performance. This approach addresses the "black-box" nature of existing topology generators, offering transparency into how agent collaboration structures emerge from optimization processes.
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference
arXiv:2608.12921v2 Announce Type: replace-cross Abstract: 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.
Abstract: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.
Multiagent Systems (cs.MA); Artificial Intelligence (cs.AI)
arXiv:2608.12921 [cs.MA]
(or arXiv:2608.12921v2 [cs.MA] for this version)
https://doi.org/10.48550/arXiv.2608.12921 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 286 words
Related coverage
[AINews] not much happened today
Latent Space · Sep 10, 2026
Academia is for Ambition — Alex Zhang, MIT
Latent Space · Oct 2, 2026
Spur: Modern GPU Job Scheduling for HPC and AI Workloads
AMD · Jul 22, 2026
Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · Aug 26, 2026