SciOrch：学习如何协调专业的LLM来解决前沿的多模态科学推理任务
SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks
摘要
前沿科学推理仍然是大型语言模型面临的重要挑战——即使是最先进的商业模型也难以达到专家级水平。对模型行为的进一步分析表明，不同模型在不同类型的问题中各有优势，没有一种模型能够完全覆盖所有情况。我们提出了SciOrch这一框架，该框架通过训练一个轻量级的8B模型来协调各种前沿语言模型以进行科学推理。该框架能够将每个问题分解为多个子问题，然后通过API调用将这些子问题分配给不同的商业模型，最终生成完整的答案。训练这样的协调系统比传统的代理式强化学习更为困难：每个动作都会触发API调用，而API调用的成本和时间都很高，因此传统的在线部署方式无法实现。我们采用基于MCTS的方法来解决这一问题：生成多种协调路径，提取每个节点上的单次样本数据，并使用GRPO风格的训练方法来优化协调系统。在包含SGI-Reasoning和Scientists’ First Exam的240个问题的测试集上，SciOrch的平均准确率达到了56.66%，比最先进的单一商业模型提升了3.74%，比最先进的多智能体基线模型提升了3.33%。同时，它在SGI和SFE两个领域都取得了最高的准确率，且API成本仅为典型多智能体方法的不到一半。
English Abstract
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.