Metraipolis › archive › dc_fc03ab7cb397

MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning — arXiv:2609.26667

Source: arXiv (en)
Original: https://arxiv.org/abs/2609.26667
License (as archived): CC0-1.0
Archived: 2026-10-08T15:08:03.672Z
SHA-256 of the archived text: a3fb6fa676c247554817778a9bdb48919653e5c41df92478d262cb7e1dc08d75
Stable URL of this page: https://metraipolis.com/documento/dc_fc03ab7cb397

How to cite

MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning — arXiv:2609.26667 — arXiv (en), https://arxiv.org/abs/2609.26667 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_fc03ab7cb397 (Metraipolis archive dc_fc03ab7cb397, sha256 a3fb6fa676c247554817778a9bdb48919653e5c41df92478d262cb7e1dc08d75)

BibTeX

@misc{dcfc03ab7cb397,
  title = {MAGIC: Mixed-Granularity Agent Graphs via Incremental Construction with Dense-Reward Reinforcement Learning — arXiv:2609.26667},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.26667},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_fc03ab7cb397; sha256 a3fb6fa676c247554817778a9bdb48919653e5c41df92478d262cb7e1dc08d75},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.26667. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Collaboration topology shapes both the performance and execution cost of LLM-based multi-agent systems. Because tasks differ in complexity and required capabilities, recent approaches generate task-specific collaboration graphs that specify agent participation and information flow. However, representative topology generators use either individual agents or predefined groups throughout an organization, overlooking differing collaboration needs across subtasks. Our key insight is to select granularity locally for each functional role, combining fine-grained control with reusable collaboration patterns within one organization. Learning such organizations requires exploring a combinatorial construction space with limited intermediate feedback from final-answer rewards. Therefore, we propose MAGIC, a dense-reward reinforcement learning framework for mixed-granularity graph generation. Specifically, MAGIC constructs a mixed-granularity agent graph by sequentially selecting a functional role, instantiating it as a single agent or reusable group, and connecting it to existing units. We directly optimize the construction policy using returns from trajectories sampled under the current policy and use potential-based reward shaping to provide intermediate feedback from probe-based utility and structural signals while preserving the cumulative task reward. MAGIC outperforms state-of-the-art baselines across eight benchmarks and demonstrates strong inference efficiency in our efficiency study.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-23 in cs.LG).
Categorie arXiv: Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.26667 — 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 2026-10-08T14:37:29.499Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-23?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).