Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Xu, Qiang, Bai, Shengyuan, Chen, Leqing, Liu, Zijing, Li, Yu
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:https://arxiv.org/abs/2511.16205
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866911309145047040
author Xu, Qiang
Bai, Shengyuan
Chen, Leqing
Liu, Zijing
Li, Yu
author_facet Xu, Qiang
Bai, Shengyuan
Chen, Leqing
Liu, Zijing
Li, Yu
contents Olympiad-level benchmarks in mathematics and physics are crucial testbeds for advanced AI reasoning, but chemistry, with its unique multimodal symbolic language, has remained an open challenge. We introduce ChemO, a new benchmark built from the International Chemistry Olympiad (IChO) 2025. ChemO features two key innovations for automated assessment: Assessment-Equivalent Reformulation (AER), which converts problems requiring visual outputs (e.g., drawing molecules) into computationally tractable formats, and Structured Visual Enhancement (SVE), a diagnostic mechanism to disentangle a model's visual perception capabilities from its core chemical reasoning. To tackle this benchmark, we propose ChemLabs, a hierarchical multi-agent framework that mimics human expert collaboration through specialized agents for problem decomposition, perception, reasoning, and auditing. Experiments on state-of-the-art multimodal models demonstrate that combining SVE with our multi-agent system yields dramatic performance gains. Our top configuration achieves a score of 93.6 out of 100, surpassing an estimated human gold medal threshold and establishing a new state-of-the-art in automated chemical problem-solving. ChemO Dataset: https://huggingface.co/datasets/IDEA-AI4SCI/ChemO
format Preprint
id arxiv_https___arxiv_org_abs_2511_16205
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025
Xu, Qiang
Bai, Shengyuan
Chen, Leqing
Liu, Zijing
Li, Yu
Artificial Intelligence
Olympiad-level benchmarks in mathematics and physics are crucial testbeds for advanced AI reasoning, but chemistry, with its unique multimodal symbolic language, has remained an open challenge. We introduce ChemO, a new benchmark built from the International Chemistry Olympiad (IChO) 2025. ChemO features two key innovations for automated assessment: Assessment-Equivalent Reformulation (AER), which converts problems requiring visual outputs (e.g., drawing molecules) into computationally tractable formats, and Structured Visual Enhancement (SVE), a diagnostic mechanism to disentangle a model's visual perception capabilities from its core chemical reasoning. To tackle this benchmark, we propose ChemLabs, a hierarchical multi-agent framework that mimics human expert collaboration through specialized agents for problem decomposition, perception, reasoning, and auditing. Experiments on state-of-the-art multimodal models demonstrate that combining SVE with our multi-agent system yields dramatic performance gains. Our top configuration achieves a score of 93.6 out of 100, surpassing an estimated human gold medal threshold and establishing a new state-of-the-art in automated chemical problem-solving. ChemO Dataset: https://huggingface.co/datasets/IDEA-AI4SCI/ChemO
title ChemLabs on ChemO: A Multi-Agent System for Multimodal Reasoning on IChO 2025
topic Artificial Intelligence
url https://arxiv.org/abs/2511.16205