agentic-bo

Orchestrate an end-to-end chemistry or materials optimization study from a plain-English research question to BO execution and a paper draft.

BO execution layer — initializes a run from a resolved experiment spec, records observations, and continues through suggest/observe/report.

Initialize a BO run from a dataset or explicit search-space JSON.

Generate a final BO report and summarize optimization status.

Run an external evaluator loop for a BO run using a pre-provisioned backend id.

Design and stabilize an expensive or fragile chemistry evaluator before BO setup.

Produce a lightweight chemistry or materials literature summary for research-agent, focused on baselines, key variables, and known constraints.

Draft a concise IMRAD-style paper for a BO-backed chemistry or materials study from research-agent artifacts, or generate LaTeX technical reports.

Generate next experimental suggestions from current run state.

Record observed objective values and update run history.

Profile dataset columns and apply data transformations (log, sqrt, standardize, etc.) before BO.

Decode BO suggestions back to nearest real reactions via DRFP similarity.

Decode BO descriptor suggestions back to nearest real molecules.

Encode reaction SMILES into DRFP fingerprint features for BO.

Encode molecule SMILES columns into RDKit descriptor features for BO.