Metraipolis › archive › dc_f08f9c63f657
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference — arXiv:2608.12921
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.12921
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-19T04:16:39.264Z
- SHA-256 of the archived text
99adc2ab3ad2378a69bd500a4d1060df5ef81bd74b460d5d5dbb6422ab0b52ec- Stable URL of this page
https://metraipolis.com/documento/dc_f08f9c63f657
How to cite
Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference — arXiv:2608.12921 — arXiv (en), https://arxiv.org/abs/2608.12921 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f08f9c63f657 (Metraipolis archive dc_f08f9c63f657, sha256 99adc2ab3ad2378a69bd500a4d1060df5ef81bd74b460d5d5dbb6422ab0b52ec)
BibTeX
@misc{dcf08f9c63f657,
title = {Discovering Efficient and Explainable Communication Topologies for LLM-based Multi-Agent Systems via Causal Inference — arXiv:2608.12921},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.12921},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f08f9c63f657; sha256 99adc2ab3ad2378a69bd500a4d1060df5ef81bd74b460d5d5dbb6422ab0b52ec},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.12921. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-14 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.12921 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-19T04:12:45.943Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).