TSAgent: An Agentic Workflow for Autonomous Transition State Search

TL;DR

TSAgent is an autonomous workflow that efficiently searches for transition states in catalytic reactions at DFT level, outperforming human experts in success rate and reproducing key scaling relationships.

Contribution

The paper introduces TSAgent, a novel agentic workflow that automates transition state searches directly at the DFT level with adaptive planning and analysis.

Findings

Achieves 83% success rate on a diverse catalysis benchmark.

Outperforms human experts with a 70% success rate versus 73% +/- 12%.

Reproduces established scaling relationships in catalysis studies.

Abstract

Identifying transition states (TSs) on potential energy surfaces is a central computational bottleneck in mechanistic studies of catalytic materials. A TS search is not a single calculation but a long-horizon, multi-step workflow of atomistic simulations with delayed, asynchronous feedback and heterogeneous failure modes that require a joint multimodal analysis of scalar convergence diagnostics and atomic geometries along the reaction path. To address this challenge, we propose TSAgent, an agentic workflow that automates TS search directly at the density functional theory (DFT) level of quantum chemical accuracy. TSAgent operates through a persistent plan-execute-analyze-replan loop, continuously adapting its strategy based on convergence diagnostics and geometric feedback without human intervention. We evaluate TSAgent on a diverse 100-example subset of the OC20NEB heterogeneous catalysis benchmark, where it successfully locates TSs with 83% accuracy. In a direct comparison against expert DFT practitioners on 10 held-out examples, TSAgent achieves a 70% success rate compared to a human-expert average of 73 +/- 12%. Finally, TSAgent independently reproduces Bronsted-Evans-Polanyi scaling relationships for NH3 dissociation on metal and single-atom alloy surfaces from a published heterogeneous catalysis study, demonstrating that its utility extends beyond curated benchmarks to real scientific investigations.