====== ChemCrow: Augmenting LLMs with Chemistry Tools ======
**ChemCrow** is an LLM-powered chemistry agent introduced by Bran et al. (2023) that augments GPT-4 with **18 expert-designed chemistry tools** to autonomously perform tasks in organic synthesis, drug discovery, and materials design(([[https://arxiv.org/abs/2304.05376|Bran et al. "ChemCrow: Augmenting large-language models with chemistry tools" (2023]])). With **795 citations**, it demonstrates that domain-specific tool augmentation enables LLMs to bridge the gap between computational and experimental chemistry, including executing synthesis on robotic platforms.

[[https://arxiv.org/abs/2304.05376|arXiv:2304.05376]]

===== The 18 Chemistry Expert Tools =====
ChemCrow integrates tools across four categories:

==== General Tools ====
  * **WebSearch**: Query the web for chemical information
  * **LitSearch**: Search scientific literature databases
  * **Python REPL**: Execute computational chemistry code
  * **HumanInput**: Query a human expert when uncertain

==== Molecular Analysis and Design ====
  * **Name2SMILES / CAS2SMILES / SMILES2Name**: Chemical name and identifier conversions
  * **FuncGroups**: Identify functional groups in molecules
  * **Similarity**: Compute molecular similarity scores using Tanimoto coefficient
  * **SMILES2Weight**: Calculate molecular weight from SMILES representation
  * **ModifyMol**: Generate structural modifications for retro/forward synthesis

==== Safety and Compliance ====
  * **ChemicalWeaponCheck**: Screen compounds against chemical weapons databases (CAS-based)
  * **ExplosiveCheck**: Detect explosive properties via PubChem
  * **PatentChecker**: Verify patent status of compounds

==== Reaction and Synthesis ====
  * **RXNPredict**: Predict reaction products using RXN4Chemistry
  * **RXNPlanner**: Generate multi-step synthetic routes with conditions and solvents
  * **NamedRxnFinder**: Identify named reactions in transformations

===== ReAct Reasoning Loop =====
ChemCrow employs the ReAct framework for iterative reasoning(([[https://arxiv.org/abs/2210.03629|Yao et al. "ReAct: Synergizing Reasoning and Acting in Language Models" (2022]])). At each step $t$, the agent generates:

$$a_t = \text{LLM}(\text{Thought}_t, \text{Action}_t, \text{Input}_t \mid h_{<t})$$

where $h_{<t}$ is the history of previous thought-action-observation triples. The agent selects from the 18 tools based on the current reasoning state and observation feedback.

===== System Architecture =====
<mermaid>
graph TD
    A[User Chemistry Query] --> B[GPT-4 Reasoning Engine]
    B --> C{Select Tool}
    C --> D[General Tools]
    C --> E[Molecular Analysis]
    C --> F[Safety Checks]
    C --> G[Reaction and Synthesis]
    D --> H[Observation]
    E --> H
    F --> H
    G --> H
    H --> I{Safety Verified?}
    I, No --> J[Halt: Safety Violation]
    I, Yes --> K{Task Complete?}
    K, No --> B
    K, Yes --> L[Final Answer with Citations]
    G --> M[RXN4Chemistry API]
    G --> N[RoboRXN Robotic Platform]
    E --> O[PubChem Database]
</mermaid>

===== Code Example =====
<code python>
# Simplified ChemCrow agent with tool selection
TOOLS = {
    "Name2SMILES": lambda name: pubchem_lookup(name, "smiles"),
    "RXNPredict": lambda rxn: rxn4chemistry_predict(rxn),
    "RXNPlanner": lambda target: rxn4chemistry_plan(target),
    "ChemicalWeaponCheck": lambda cas: check_cw_database(cas),
    "ExplosiveCheck": lambda smiles: check_explosive(smiles),
    "Similarity": lambda pair: tanimoto_similarity(*pair),
    "FuncGroups": lambda smiles: identify_groups(smiles),
}

def chemcrow_run(query, llm, max_steps=15):
    history = []
    for step in range(max_steps):
        thought, action, action_input = llm.reason(query, history)
        # Safety gate: always check before synthesis
        if action in ("RXNPlanner", "RXNPredict"):
            smiles = TOOLS["Name2SMILES"](action_input)
            if not TOOLS["ChemicalWeaponCheck"](smiles):
                return "Halted: safety violation detected"
            if not TOOLS["ExplosiveCheck"](smiles):
                return "Halted: explosive compound detected"
        observation = TOOLSaction(action_input)
        history.append((thought, action, observation))
        if is_final_answer(thought):
            return compile_answer(history)
</code>

===== Demonstrated Capabilities =====
  * **Autonomous synthesis**: Successfully planned and executed synthesis of an insect repellent and three organocatalysts
  * **Drug discovery**: Guided novel chromophore discovery with target optical properties
  * **Safety enforcement**: Proactive screening against chemical weapons and explosives databases
  * **Robotic execution**: Integrated with IBM RoboRXN for automated wet-lab synthesis(([[https://rxn.res.ibm.com|IBM RXN for Chemistry Platform]]))
  * Outperforms vanilla GPT-4 on chemistry-specific tasks per expert evaluation

===== See Also =====
  * [[data_science_agents|Data Science Agents: DatawiseAgent]]
  * [[tool_use|Tool Use for LLM Agents]]
  * [[agenttuning|AgentTuning: Enabling Generalized Agent Capabilities in LLMs]]

===== References =====