ChemHAS: Hierarchical Agent Stacking for Enhancing Chemistry Tools

• URL: http://arxiv.org/abs/2505.21569v1
• Date: Tue, 27 May 2025 06:22:57 GMT
• Title: ChemHAS: Hierarchical Agent Stacking for Enhancing Chemistry Tools
• Authors: Zhucong Li, Bowei Zhang, Jin Xiao, Zhijian Zhou, Fenglei Cao, Jiaqing Liang, Yuan Qi,
• Abstract summary: We propose ChemHAS, a simple yet effective method that enhances chemistry tools through optimizing agent-stacking structures from limited data.<n>ChemHAS achieves performance across four fundamental chemistry tasks, demonstrating that our method can effectively compensate for prediction errors of the tools.
• Score: 13.4380618947395
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Large Language Model (LLM)-based agents have demonstrated the ability to improve performance in chemistry-related tasks by selecting appropriate tools. However, their effectiveness remains limited by the inherent prediction errors of chemistry tools. In this paper, we take a step further by exploring how LLMbased agents can, in turn, be leveraged to reduce prediction errors of the tools. To this end, we propose ChemHAS (Chemical Hierarchical Agent Stacking), a simple yet effective method that enhances chemistry tools through optimizing agent-stacking structures from limited data. ChemHAS achieves state-of-the-art performance across four fundamental chemistry tasks, demonstrating that our method can effectively compensate for prediction errors of the tools. Furthermore, we identify and characterize four distinct agent-stacking behaviors, potentially improving interpretability and revealing new possibilities for AI agent applications in scientific research. Our code and dataset are publicly available at https: //anonymous.4open.science/r/ChemHAS-01E4/README.md.

Related papers

• ChemActor: Enhancing Automated Extraction of Chemical Synthesis Actions with LLM-Generated Data [53.78763789036172]
  We present ChemActor, a fully fine-tuned large language model (LLM) as a chemical executor to convert between unstructured experimental procedures and structured action sequences.<n>This framework integrates a data selection module that selects data based on distribution divergence, with a general-purpose LLM, to generate machine-executable actions from a single molecule input.<n>Experiments on reaction-to-description (R2D) and description-to-action (D2A) tasks demonstrate that ChemActor achieves state-of-the-art performance, outperforming the baseline model by 10%.
  arXiv  Detail & Related papers  (2025-06-30T05:11:19Z)
• CheMatAgent: Enhancing LLMs for Chemistry and Materials Science through Tree-Search Based Tool Learning [12.745398618084474]
  Large language models (LLMs) have recently demonstrated promising capabilities in chemistry tasks.<n>We propose an LLM-based agent that integrates 137 external chemical tools created ranging from basic information retrieval to complex reaction predictions.
  arXiv  Detail & Related papers  (2025-06-09T08:41:39Z)
• ChemGraph: An Agentic Framework for Computational Chemistry Workflows [0.0]
  ChemGraph is an agentic framework powered by artificial intelligence and state-of-the-art simulation tools.<n>Users can perform tasks such as molecular structure generation, single-point energy, geometry optimization, vibrational analysis, and thermochemistry calculations.
  arXiv  Detail & Related papers  (2025-06-03T21:11:56Z)
• ChemAgent: Self-updating Library in Large Language Models Improves Chemical Reasoning [64.2106664137118]
  ChemAgent is a novel framework designed to improve the performance of large language models (LLMs)<n>It is developed by decomposing chemical tasks into sub-tasks and compiling these sub-tasks into a structured collection that can be referenced for future queries.<n>When presented with a new problem, ChemAgent retrieves and refines pertinent information from the library, which we call memory.
  arXiv  Detail & Related papers  (2025-01-11T17:10:30Z)
• ChemToolAgent: The Impact of Tools on Language Agents for Chemistry Problem Solving [10.963114215850515]
  We develop an enhanced chemistry agent over ChemCrow, and conduct a comprehensive evaluation of its performance on both specialized chemistry tasks and general chemistry questions.<n>Surprisingly, ChemToolAgent does not consistently outperform its base LLMs without tools.<n>For specialized chemistry tasks, such as synthesis prediction, we should augment agents with specialized tools; however, for general chemistry questions like those in exams, agents' ability to reason correctly with chemistry knowledge matters more.
  arXiv  Detail & Related papers  (2024-11-11T18:46:37Z)
• ChemEval: A Comprehensive Multi-Level Chemical Evaluation for Large Language Models [62.37850540570268]
  Existing benchmarks in this domain fail to adequately meet the specific requirements of chemical research professionals. ChemEval identifies 4 crucial progressive levels in chemistry, assessing 12 dimensions of LLMs across 42 distinct chemical tasks. Results show that while general LLMs excel in literature understanding and instruction following, they fall short in tasks demanding advanced chemical knowledge.
  arXiv  Detail & Related papers  (2024-09-21T02:50:43Z)
• Learning to Use Tools via Cooperative and Interactive Agents [58.77710337157665]
  Tool learning empowers large language models (LLMs) as agents to use external tools and extend their utility. We propose ConAgents, a Cooperative and interactive Agents framework, which coordinates three specialized agents for tool selection, tool execution, and action calibration separately. Our experiments on three datasets show that the LLMs, when equipped with ConAgents, outperform baselines with substantial improvement.
  arXiv  Detail & Related papers  (2024-03-05T15:08:16Z)
• An Autonomous Large Language Model Agent for Chemical Literature Data Mining [60.85177362167166]
  We introduce an end-to-end AI agent framework capable of high-fidelity extraction from extensive chemical literature. Our framework's efficacy is evaluated using accuracy, recall, and F1 score of reaction condition data.
  arXiv  Detail & Related papers  (2024-02-20T13:21:46Z)
• Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis [55.30328162764292]
  Chemist-X is a comprehensive AI agent that automates the reaction condition optimization (RCO) task in chemical synthesis.<n>The agent uses retrieval-augmented generation (RAG) technology and AI-controlled wet-lab experiment executions.<n>Results of our automatic wet-lab experiments, achieved by fully LLM-supervised end-to-end operation with no human in the lope, prove Chemist-X's ability in self-driving laboratories.
  arXiv  Detail & Related papers  (2023-11-16T01:21:33Z)
• ChemCrow: Augmenting large-language models with chemistry tools [0.9195187117013247]
  Large-language models (LLMs) have shown strong performance in tasks across domains, but struggle with chemistry-related problems. In this study, we introduce ChemCrow, an LLM chemistry agent designed to accomplish tasks across organic synthesis, drug discovery, and materials design. Our agent autonomously planned and executed the syntheses of an insect repellent, three organocatalysts, and guided the discovery of a novel chromophore.
  arXiv  Detail & Related papers  (2023-04-11T17:41:13Z)
• Improving Molecular Representation Learning with Metric Learning-enhanced Optimal Transport [49.237577649802034]
  We develop a novel optimal transport-based algorithm termed MROT to enhance their generalization capability for molecular regression problems. MROT significantly outperforms state-of-the-art models, showing promising potential in accelerating the discovery of new substances.
  arXiv  Detail & Related papers  (2022-02-13T04:56:18Z)
• What is Going on Inside Recurrent Meta Reinforcement Learning Agents? [63.58053355357644]
  Recurrent meta reinforcement learning (meta-RL) agents are agents that employ a recurrent neural network (RNN) for the purpose of "learning a learning algorithm" We shed light on the internal working mechanisms of these agents by reformulating the meta-RL problem using the Partially Observable Markov Decision Process (POMDP) framework.
  arXiv  Detail & Related papers  (2021-04-29T20:34:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.