AI Paper Atlas

Research map / Large language models / Agents, code and math

MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs

Christoph Bartmann, Johannes Schimunek, Mykyta Ielanskyi, Philipp Seidl, Günter Klambauer, Sohvi Luukkonen

ICLR 2026 · Large language models › Agents, code and math · approach: LLMs for scientific discovery

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use a higher reasoning budget (High vs Med) (ablation)GPT-OSS 20B · MolecularIQ overallaccuracy (%): 27.2 -> 35.7Improved
use a higher reasoning budget (High vs Med) (ablation)GPT-OSS 120B · MolecularIQ overallaccuracy (%): 26.5 -> 47.5Improved
chemistry fine-tuning of general LLMs (ablation)chemistry-specialized LLMs · MolecularIQ overallaccuracyHurt
chemistry fine-tuning (ChemDFM-R) (ablation)ChemDFM-R · MolecularIQ overallaccuracyNo clear effect
chemistry tuning effect on output format (ablation)chemistry-tuned LLMs · MolecularIQtype-validity rate: 18 percentage points lower on averageHurt
randomize, kekulize or relabel rings in SMILES (ablation)top-10 LLMs · MolecularIQ counting and indexingaccuracyHurt
increase multitask load (ablation)top LLMs · MolecularIQ countingaccuracyHurt
increase multitask load vs independence baseline (ablation)top LLMs · MolecularIQsuccess rate: observed n-task success exceeds p_single^nImproved
increase molecular Bertz complexity (ablation)top LLMs · MolecularIQ countingaccuracyHurt
switch from counting to indexing for same property (ablation)top LLMs · MolecularIQaccuracy: decrease of ~5-30% depending on modelHurt
lower prevalence of constraint combination or 3+ constraints (ablation)top LLMs · MolecularIQ generationaccuracyHurt
use 8 rollouts instead of 3 (ablation)subset of models · MolecularIQaccuracyNo clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy