ChemAmp: Amplified Chemistry Tools via Composable Agents

arXiv:2505.21569v3 Announce Type: replace-cross Abstract: Although LLM-based agents are proven to master tool orchestration in scientific fields, particularly chemistry, their single-task performance remains limited by underlying tool constraints. To this end, we propose tool amplification, a novel paradigm that enhances the collective capabilities of specialized tools through optimized, dynamic coordination within individual tasks. Instantiating this paradigm, we introduce ChemAmp, a computationally lightweight framework that dynamically treats chemistry tools (e.g., UniMol2, Chemformer) as composable building-block agents. It constructs task-specialized super-agents that transcend atomic tool constraints with limited data (leq10 samples). Our evaluations across four core chemistry tasks molecular design, molecule captioning, reaction prediction, and property prediction demonstrate that ChemAmp outperforms chemistry-specialized models, generalist LLMs, and agent systems with tool orchestration. Critically, this bottom-up construction strategy enables 94% inference token cost reductions versus vanilla multi-agent systems.

Related

• El Agente Quntur: A research collaborator agent for quantum chemistry
• EnvScaler: Scaling Tool-Interactive Environments for LLM Agent via Programmatic Synthesis
• El Agente Estructural: An Artificially Intelligent Molecular Editor
• SkillMOO: Multi-Objective Optimization of Agent Skills for Software Engineering

Source: arXiv cs.AI | 2026-04-20