Metraipolis › archive › dc_bb7320f8d478

ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models — arXiv:2608.11949

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.11949
License (as archived)
CC0-1.0
Archived
2026-10-19T05:15:31.643Z
SHA-256 of the archived text
1c5fc51bf981acdea2f54f3e86c840542dbb65457d1cfbb46f6719d2fbf7fdcc
Stable URL of this page
https://metraipolis.com/documento/dc_bb7320f8d478

How to cite

ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models — arXiv:2608.11949 — arXiv (en), https://arxiv.org/abs/2608.11949 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_bb7320f8d478 (Metraipolis archive dc_bb7320f8d478, sha256 1c5fc51bf981acdea2f54f3e86c840542dbb65457d1cfbb46f6719d2fbf7fdcc)
BibTeX
@misc{dcbb7320f8d478,
  title = {ExRole: From Team Trajectories to Executable Roles in Multi-Agent Language Models — arXiv:2608.11949},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.11949},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_bb7320f8d478; sha256 1c5fc51bf981acdea2f54f3e86c840542dbb65457d1cfbb46f6719d2fbf7fdcc},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.11949. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Roles provide an interpretable interface for organizing language-model agents, yet most multi-agent systems treat them as hand-written prompt labels disconnected from learned behavior and parameter updates. We argue that a useful role should instead be an executable control variable: it should summarize behavior predictive of future utility, guide subsequent interaction, and identify the trainable capacity responsible for that behavior. We introduce ExRole, a trajectory-to-role framework that learns future-aware role prototypes from prefix-local team traces, resolves them into readable instructions and token-aligned role markers, and optionally routes shared LoRA rank slots with turn-aligned credit. Across MuSiQue and 2WikiMultiHopQA, ExRole improves over single-agent search by 15.0/14.4 and 13.5/16.1 EM/F1 points, respectively. Against the strongest non-ExRole controls, the corresponding gains remain 11.5/11.6 and 7.7/9.7 points. Across both benchmarks, the controlled results consistently favor trajectory-induced role conditioning over role-free, manual, random, and shuffled alternatives. Role-Agent-Turn interventions further show that the induced roles capture transferable behavioral specialization beyond fixed agent identities or turn positions.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-13 in cs.AI).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.11949 — 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 2026-10-19T05:08:46.648Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-13?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).