MotionPlan: Training-Free LLM-Guided Residue Motion Planning for Protein Dynamics Generation

Protein dynamics generators can produce plausible states and temporally ordered rollouts, yet their objectives largely fit marginal distributions rather than the inter-residue coordination organizing transitions; coordination errors therefore accumulate over long horizons. Retraining for explicit residue-level control is costly and requires paired motion supervision rarely available in MD data. We introduce MotionPlan, a training-free framework in which a large language model (LLM) infers per-residue coordination roles and confidence from sequence and structural context. The plan becomes a localized, confidence-weighted intervention on a frozen generator's pair representations throughout reverse-SDE sampling, without parameter updates or coordinate editing. Because Pairformer-based generators share pair representations, this provides a reusable inference-time control interface. On the complete 82-protein ATLAS test split, MotionPlan reduces trajectory-level $C\alpha$ MAE from 4.60 Å to 3.309 Å on the stride-256, $L=9$ benchmark and improves frame/consecutive-frame Pearson correlation from 0.62/0.53 to 0.67/0.59. On the 100 ns benchmark, it lowers JSD from $0.52$ to $0.44$ and raises state recall from $0.36$ to $0.59$ while retaining comparable molecular quality. These results show that LLM reasoning can translate structural evidence into actionable motion priors for frozen protein dynamics generators.