Metraipolis › archive › dc_c685b25e89d7
Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems — arXiv:2610.41378
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.41378
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-02T04:43:33.652Z
- SHA-256 of the archived text
07087862821144e15ce20b9a5733159b7bf7be81ac35175d2bb04e50b2078c9d- Stable URL of this page
https://metraipolis.com/documento/dc_c685b25e89d7
How to cite
Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems — arXiv:2610.41378 — arXiv (en), https://arxiv.org/abs/2610.41378 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c685b25e89d7 (Metraipolis archive dc_c685b25e89d7, sha256 07087862821144e15ce20b9a5733159b7bf7be81ac35175d2bb04e50b2078c9d)
BibTeX
@misc{dcc685b25e89d7,
title = {Ask on Demand: Targeted Peer Communication for Parallel Agentic Systems — arXiv:2610.41378},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.41378},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c685b25e89d7; sha256 07087862821144e15ce20b9a5733159b7bf7be81ac35175d2bb04e50b2078c9d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.41378. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Parallel LLM agents tackle complex tasks by exploring multiple trajectories, yet useful discoveries remain isolated in individual execution histories. Existing sharing methods often select or summarize information before other agents' needs become clear, potentially overlooking details that become important later. We propose Ask on Demand (AOD), a communication framework that enables agents to seek targeted peer assistance when specific information needs arise. Upon an approved request, AOD retrieves relevant evidence from peer execution histories, selects a suitable peer, and generates a response tailored to the request. To determine when such assistance is worthwhile, we train a lightweight gate using paired team continuations, with supervision derived from final team outcomes and inference cost. Experiments on AppWorld and WebShop demonstrate that AOD consistently improves task performance over independent parallel execution while achieving lower inference cost than existing information-sharing baselines. These findings highlight the benefits of aligning peer communication with agents' evolving information needs to achieve more effective and efficient collaboration. Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2610.41378 — 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 2026-11-02T04:42:12.370Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).