SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks

Hugging Face Daily Papers Papers
multimodal scientific-reasoning llm-orchestration mcts vision-language-model multi-agent

Summary

SciOrch presents an 8B vision-language model trained with MCTS to coordinate multiple expert LLMs for multimodal scientific reasoning, achieving superior performance while reducing API costs.

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.
Original Article
View Cached Full Text

Cached at: 06/18/26, 07:55 AM

Paper page - SciOrch: Learning to Orchestrate Expert LLMs for Solving Frontier Multimodal Scientific Reasoning Tasks

Source: https://huggingface.co/papers/2606.15872 We’re excited to share our latest work,SciOrch: Learning to Orchestrate Expert LLMs for Frontier Multimodal Scientific Reasoning🧬

Scientific reasoning often requires reading complex figures, combining knowledge from different fields, and solving problems step by step. Different LLMs are good at different parts of this process — so instead of relying on just one model, we ask: can a small model learn to coordinate multiple expert LLMs?

To answer this, we proposeSciOrch🎼, an 8B vision-language model that learns to break down scientific questions, call the right expert models, and combine their answers.

Since calling commercial models can be costly, we train SciOrch with an efficient MCTS-based pipeline 🌳.

Our results show that SciOrch outperforms strong single-model and multi-agent baselines, while reducing API cost. We hope this is a step toward more efficient and collaborative AI systems for scientific reasoning 🚀

Similar Articles

SciR: A Controllable Benchmark for Scientific Reasoning in LLMs

arXiv cs.AI

SciR is a new controllable benchmark for evaluating LLMs on scientific reasoning including deduction, induction, and causal abduction, with parametric control over extraction and inference difficulty. Tests show both axes degrade performance across models, with reasoning models like DeepSeek-R1 outperforming instruct models on inference.

Learning to reason with LLMs

OpenAI Blog

OpenAI publishes an article exploring reasoning techniques with LLMs through cipher-decoding examples, demonstrating step-by-step problem-solving approaches and pattern recognition in language models.

OmniThoughtVis: A Scalable Distillation Pipeline for Deployable Multimodal Reasoning Models

arXiv cs.CL

This paper introduces OmniThoughtVis, a scalable pipeline for distilling multimodal reasoning capabilities from large teacher models to smaller, deployment-oriented MLLMs. The method uses curated chain-of-thought data to significantly improve reasoning performance on benchmarks like MathVerse and MMMU-Pro for models ranging from 2B to 8B parameters.

Simulate, Reason, Decide: Scientific Reasoning with LLMs for Simulation-Driven Decision Making

arXiv cs.AI

Researchers from the University of Michigan introduce MechSim, a mechanism-grounded neuro-symbolic reasoning framework that enables LLM agents to reason about the internal assumptions, dependencies, and execution behavior of scientific simulators rather than treating them as black boxes. The framework improves explanation quality and decision-making reliability across high-stakes domains like healthcare, finance, and public policy.