Agents on a Tree: Pathwise Coordination for Multi-Objective Molecular Optimization
Quick Take
ATOM introduces a multi-agent framework for multi-objective molecular optimization, utilizing a tree-structured search to enhance exploration and trade-off representation. It outperforms strong baselines in Pareto coverage and hypervolume across activity, synthesizability, and ADMET-related properties benchmarks.
Key Points
- ATOM uses a tree-structured search for molecular optimization with specialized agents.
- Agents coordinate along different paths, avoiding global consensus for better exploration.
- Global memory of past behaviors enhances balanced exploration across objectives.
- Experiments show improved Pareto coverage and hypervolume compared to strong baselines.
- Code for ATOM is publicly available for further research and development.
Article Content
From source RSS / original summaryarXiv:2606. 00008v1 Announce Type: new Abstract: Multi-objective molecular optimization requires searching vast chemical spaces under conflicting objectives, where early design decisions strongly constrain downstream outcomes. Existing methods typically rely on a single policy or fixed scalarization, which limits their ability to represent diverse trade-offs and to explore multiple promising design trajectories.
We propose ATOM, a multi-agent framework that formulates molecular optimization as a tree-structured search. Each node corresponds to an atomic operation and hosts an agent specialized for a particular objective or decision context. Agents coordinate along different paths of the tree rather than enforcing a global consensus, enabling the method to maintain and compare alternative molecular evolution trajectories.
A global memory of past optimization behaviors further supports balanced exploration and exploitation across objectives. This tree-structured interaction enables reasoning over long-horizon dependencies inherent in molecular design. Experiments on challenging multi-objective benchmarks involving activity, synthesizability, and ADMET-related properties show that ATOM consistently achieves improved Pareto coverage and hypervolume over strong baselines.
These results demonstrate the effectiveness of pathwise multi-agent coordination for molecular optimization. Code is available at https://anonymous. 4open. science/r/ATOM-41CE.
Reader Mode unavailable (could not extract clean content).
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →MindGames Arena Generalization Track: In2AI Solution with Delayed Per-Step Reward Attribution
The In2AI solution introduces delayed per-step reward attribution for training language model agents in multi-agent environments, achieving top performance on the MindGames Arena benchmark at NeurIPS 2025. An 8-billion-parameter model outperformed larger proprietary systems, including GPT-5, in competitive play, demonstrating enhanced stability and sample efficiency in reinforcement learning.