Frontier scientific reasoning remains a major challenge for large language models (LLMs), where even the strongest commercial systems fall short of expert-level performance. A closer look at model behavior reveals substantial complementarity that single-model evaluation hides: different frontier models excel on different question types, and no single model captures the full picture. We present SciOrch, a framework that trains a lightweight 8B model to orchestrate frontier LLMs for scientific reasoning. The orchestrator decomposes each question, delegates sub-problems to selected commercial models through API calls, and synthesizes a final answer. Training such an orchestrator is fundamentally harder than conventional agentic RL: each action triggers an API call that is expensive in both dollar cost and latency, making standard online rollouts infeasible. We address this with MCTS-based approach, producing diverse orchestration trajectories, extracting per-node single-turn samples, and optimizing the orchestrator with GRPO-style training. On a 240-question test set spanning SGI-Reasoning and Scientists' First Exam, SciOrch reaches 56.66% average accuracy, outperforming the strongest single commercial model by 3.74% and the strongest multi-agent baseline by 3.33%. It also attains the best accuracy on both SGI and SFE with less than half the API cost of typical multi-agent methods.

翻译：[翻译摘要] 前沿科学推理仍是大语言模型（LLMs）面临的一项重大挑战，即使是最强大的商业系统在此类任务中也未达到专家级水平。对模型行为的深入分析揭示了单模型评估所掩盖的显著互补性：不同前沿模型在不同类型问题上表现各异，没有任何单一模型能全面覆盖全部问题。我们提出SciOrch框架，该框架通过训练一个轻量级的8B模型来编排前沿大语言模型以完成科学推理任务。编排器负责分解每个问题，通过API调用将子问题委托给选定的商业模型，并综合生成最终答案。训练此类编排器在本质上比传统的基于智能体的强化学习（RL）更为困难：每次动作触发都会产生API调用，这既增加了经济成本也延长了延迟时间，导致标准的在线探索（online rollouts）不可行。我们利用基于蒙特卡洛树搜索（MCTS）的方法解决此问题，生成多样化的编排轨迹（orchestration trajectories），提取每个节点的单轮样本，并通过GRPO风格的训练优化编排器。在一个涵盖SGI-Reasoning和《科学家首考》（Scientists' First Exam, SFE）的240道测试题集上，SciOrch达到了平均56.66%的准确率，分别比最强的单一商业模型和最强的多智能体基线提升了3.74%和3.33%。同时，在SGI和SFE两项任务上，SciOrch也取得了最优准确率，且其API成本仅为典型多智能体方法的一半以下。