Metraipolis › archive › dc_d552aa90d85a

Beyond Division of Labor: How Roles Shape Feedback and Recovery in Multi-Agent Systems — arXiv:2611.03931

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03931
License (as archived)
CC0-1.0
Archived
2026-11-04T11:50:11.495Z
SHA-256 of the archived text
fa5117e934098f6063332ba38423933305e4a06086f8799b20191058689fdcd9
Stable URL of this page
https://metraipolis.com/documento/dc_d552aa90d85a

How to cite

Beyond Division of Labor: How Roles Shape Feedback and Recovery in Multi-Agent Systems — arXiv:2611.03931 — arXiv (en), https://arxiv.org/abs/2611.03931 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_d552aa90d85a (Metraipolis archive dc_d552aa90d85a, sha256 fa5117e934098f6063332ba38423933305e4a06086f8799b20191058689fdcd9)
BibTeX
@misc{dcd552aa90d85a,
  title = {Beyond Division of Labor: How Roles Shape Feedback and Recovery in Multi-Agent Systems — arXiv:2611.03931},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03931},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_d552aa90d85a; sha256 fa5117e934098f6063332ba38423933305e4a06086f8799b20191058689fdcd9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03931. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Roles in multi-agent large language model (LLM) systems allocate decisions as well as work. In a Planner--Executor--Reviewer team, the Reviewer's approval can determine when the team submits an answer and receives corrective feedback. We study both functions by varying role instructions while holding agents, topology, call budget, and ground-truth evaluator constant, using three open-weight models on Omni-MATH and two on SciBench. Removing roles largely eliminates functional specialization without lowering first-pass accuracy. After a failed first answer, however, submission decisions matter: a role-structured Reviewer often withholds approval, so its team submits less often and receives fewer evaluator verdicts. In an exploratory comparison with feedback available to both teams, the role-free team recovers more often across all five model--benchmark settings. Two further analyses support the importance of feedback opportunities. In a post hoc comparison at equal numbers of verdicts, the pooled recovery difference is small (role-structured minus role-free: $+0.009$, 95% interval $[-0.014,+0.033]$). In an exploratory intervention on $400$ Omni-MATH problems with gemma-4, keeping the role prompts but forcing submission in every cycle raises recovery from $0.198$ to $0.613$; the paired comparison detects no difference from the role-free team. The takeaway is to evaluate roles through recovery after failure as well as specialization. For systems with reliable external feedback, this requires measuring who may submit, how often the team receives feedback, and which agents can act on it.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2611.03931 — 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 2026-11-04T11:50:11.393Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).