Metraipolis › archive › dc_83ee5e1dc4dc
ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments — arXiv:2609.33618
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.33618
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:57:00.334Z
- SHA-256 of the archived text
c1da78330975070e55b0e8e7cbaaef982ee09fc46ba3380d8d1ee504852bb2a0- Stable URL of this page
https://metraipolis.com/documento/dc_83ee5e1dc4dc
How to cite
ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments — arXiv:2609.33618 — arXiv (en), https://arxiv.org/abs/2609.33618 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_83ee5e1dc4dc (Metraipolis archive dc_83ee5e1dc4dc, sha256 c1da78330975070e55b0e8e7cbaaef982ee09fc46ba3380d8d1ee504852bb2a0)
BibTeX
@misc{dc83ee5e1dc4dc,
title = {ParaAgent: Reinforcing Parallel Acting in Open-World Tool Environments — arXiv:2609.33618},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.33618},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_83ee5e1dc4dc; sha256 c1da78330975070e55b0e8e7cbaaef982ee09fc46ba3380d8d1ee504852bb2a0},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.33618. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Language model agents are increasingly deployed in open-world tool environments, which require balancing exploring unknown capabilities and exploiting known ones. Existing methods face a performance-efficiency tradeoff: they either rigidly decouple exploration and execution or interleave them without coordination. We argue that the key lies not in whether to decouple or interleave them, but in how to coordinate them across granularities. We introduce ParaAct, a structured parallel-action loop that combines phase-level Exploration $\rightleftharpoons$ Execution with action-level parallelism. To learn this loop, ParaAgent combines multi-agent cold-start demonstrations with reinforcement learning under multi-level advantage decoupling, making planning structure explicit and supervising it with step-, phase-, and trajectory-level rewards. Learning is supported by our ToolEnv, a scalable simulator grounded in 50,011 realistic tool interfaces. On two open-world tool benchmarks, ParaAgent-4B achieves the best average success among all baselines, including GPT-4.1 systems, with the largest gains on multi-tool tasks. Behavioral analyses show that these gains stem from this action organization, highlighting its importance for capable and efficient open-world agents. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2609.33618 — 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 2026-10-07T20:29:01.313Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).