MotifAgent: Learning Molecular Assembly through Multi-Agent Collaboration for Chemical Language Understanding

ACL ARR 2026 January Submission7400 Authors

Keywords: Multi-Agent Collaboration, Molecular Assembly, Chemical Reasoning, Reinforcement Learning

Abstract: Large Language Models (LLMs) have shown great potential in molecular understanding by aligning molecular representations with text. However, existing approaches remain limited to static motif recognition without comprehending the generative principles—the connection rules governing how motifs assemble into valid topological structures. To address this challenge, we introduce \textbf{MotifAgent}, a multi-agent reinforcement learning framework inspired by emergent collective intelligence. We formulate molecular assembly as a collaborative problem where each motif is represented by an agent sharing a common LLM backbone, learning connection rules through explicit inter-motif negotiation rather than implicit sequence memorization. Key innovations include: (1) dynamic inter-agent negotiation for modeling motif connections; (2) Set-based Behavioral Cloning for learning multiple topologically equivalent assembly paths; (3) topology-aware reward shaping with MAPPO to maintain chemical validity while optimizing target properties. Extensive experiments demonstrate that MotifAgent achieves state-of-the-art performance across molecular property prediction, description generation, and reaction prediction tasks, with our generalist model surpassing specialized expert models.

Paper Type: Long

Research Area: AI/LLM Agents

Research Area Keywords: multi-agent systems, agent coordination and negotiation, reinforcement learning in agents, LLM agents

Contribution Types: Model analysis & interpretability, NLP engineering experiment, Publicly available software and/or pre-trained models

Languages Studied: English

Submission Number: 7400