Metraipolis › archive › dc_eef6c47e997b
E$^3$-Orch: Towards Effective, Efficient, and Extensible Agentic Orchestration with Reinforcement Learning — arXiv:2608.04588
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.04588
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T11:14:27.838Z
- SHA-256 of the archived text
7ac477cbc13081c1c76dd1159a8738f3bed1d6cc29bbf793fbc0be1e2ed1b02e- Stable URL of this page
https://metraipolis.com/documento/dc_eef6c47e997b
How to cite
E$^3$-Orch: Towards Effective, Efficient, and Extensible Agentic Orchestration with Reinforcement Learning — arXiv:2608.04588 — arXiv (en), https://arxiv.org/abs/2608.04588 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eef6c47e997b (Metraipolis archive dc_eef6c47e997b, sha256 7ac477cbc13081c1c76dd1159a8738f3bed1d6cc29bbf793fbc0be1e2ed1b02e)
BibTeX
@misc{dceef6c47e997b,
title = {E$^3$-Orch: Towards Effective, Efficient, and Extensible Agentic Orchestration with Reinforcement Learning — arXiv:2608.04588},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.04588},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eef6c47e997b; sha256 7ac477cbc13081c1c76dd1159a8738f3bed1d6cc29bbf793fbc0be1e2ed1b02e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.04588. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic orchestration enables multiple autonomous agents to solve complex tasks through adaptive decomposition, delegation, and execution. However, existing orchestrators often rely on hand-crafted logic and prompting strategies, limiting adaptation and generalization across tasks and executor configurations. We propose E$^3$-Orch, a reinforcement learning framework for effective, efficient, and extensible agentic orchestration based on a milestone-plan-act workflow. Instead of planning all subtasks upfront, E$^3$-Orch organizes execution around milestones, a mid-level abstraction that scopes planning around meaningful intermediate objectives and allows orchestration decisions to adapt as execution progresses. For each milestone, the orchestrator builds a dependency-aware plan, assigns subtasks to suitable executors, and executes independent subtasks in parallel. We train the orchestration policy from execution feedback, using milestone and plan decisions as units for fine-grained credit assignment. Tree-structured rollouts compare alternative decisions under shared execution histories, while complementary rewards optimize task performance, execution cost, and planning completeness, including an uncertainty-aware performance reward for stochastic downstream outcomes. Across seven benchmarks, E$^3$-Orch achieves the best task performance under multiple executor configurations, improving over the strongest baselines by $0.7$--$3.8$ points and delivering $1.16$--$1.59\times$ higher intelligence efficiency. The learned policy also transfers to unseen executor configurations introduced only at evaluation time, supporting extensible agentic orchestration. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-06 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.04588 — 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 2026-10-31T11:02:13.530Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-06?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).