# El Agente Gr'afico: A Semantic Execution Runtime for Scientific Agents

arXiv: https://arxiv.org/abs/2602.17902 · HTML: https://mlsanity.com/paper/2602.17902/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 117 references that are in the map.
- First posted on arXiv 19 Feb 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 19 of 19)

- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Why Do Multi-Agent LLM Systems Fail?](https://mlsanity.com/paper/2503.13657/) (2025)
- [MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields](https://mlsanity.com/paper/2206.07697/) (2022)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [When More is Less: Understanding Chain-of-Thought Length in LLMs](https://mlsanity.com/paper/2502.07266/) (2025)
- [Towards a Science of Scaling Agent Systems](https://mlsanity.com/paper/2512.08296/) (2025)
- [Kosmos: An AI Scientist for Autonomous Discovery](https://mlsanity.com/paper/2511.02824/) (2025)
- [Language Agents as Optimizable Graphs](https://mlsanity.com/paper/2402.16823/) (2024)
- [From AI for Science to Agentic Science: A Survey on Autonomous Scientific Discovery](https://mlsanity.com/paper/2508.14111/) (2025)
- [CASCADE: Cumulative Agentic Skill Creation through Autonomous Development and Evolution](https://mlsanity.com/paper/2512.23880/) (2025)
- [DREAMS: Density Functional Theory Based Research Engine for Agentic Materials Simulation](https://mlsanity.com/paper/2507.14267/) (2025)
- [CooperBench: Why Coding Agents Cannot be Your Teammates Yet](https://mlsanity.com/paper/2601.13295/) (2026)
- [System of Agentic AI for the Discovery of Metal-Organic Frameworks](https://mlsanity.com/paper/2504.14110/) (2025)
- [OckBench: Measuring the Efficiency of LLM Reasoning](https://mlsanity.com/paper/2511.05722/) (2025)
- [Aitomia: Your Intelligent Assistant for AI-Driven Atomistic and Quantum Chemical Simulations](https://mlsanity.com/paper/2505.08195/) (2025)
- [El Agente Quntur: A research collaborator agent for quantum chemistry](https://mlsanity.com/paper/2602.04850/) (2026)
- [El Agente Estructural: An Artificially Intelligent Molecular Editor](https://mlsanity.com/paper/2602.04849/) (2026)
- [Ontology-to-tools compilation for executable semantic constraint enforcement in LLM agents](https://mlsanity.com/paper/2602.03439/) (2026)
- [Speak to a Protein: An Interactive Multimodal Co-Scientist](https://mlsanity.com/paper/2510.17826/) (2025)

## Built on by (most cited first, 4 of 4)

- [El Agente Forjador: Task-Driven Agent Generation for Quantum Simulation](https://mlsanity.com/paper/2604.14609/) (2026)
- [La Agente 'Optima: Towards Agentic Self-Driving Laboratories](https://mlsanity.com/paper/2609.04564/) (2026)
- [Science Done on a Machine by a Machine: AI Agents in Computational Chemistry](https://mlsanity.com/paper/2608.18508/) (2026)
- [El Agente Potente: High-Throughput Agentic Atomistic Simulations](https://mlsanity.com/paper/2609.14840/) (2026)

## Abstract (arXiv)

Large language models (LLMs) can plan scientific workflows and generate code, but these capabilities do not specify how scientific state is validated, transferred and recorded across heterogeneous computational and experimental operations. Here we present El Agente Gr'afico, a semantic execution runtime for scientific agents that uses typed execution graphs to enforce admissible scientific state transitions, record provenance and confine model judgement to explicit decision points. Using the same top-level LLM and task-specific rubrics on six university-level quantum chemistry exercises, El Agente Gr'afico improved performance while reducing model cost by approximately 80% and wall-clock time by more than fourfold relative to our previous multi-agent architecture. Across ensemble spectroscopy and metal-organic framework (MOF) design, the runtime supported typed-state transfer, parallel execution and cross-session persistence. Open-ended studies of a disulfide redox mechanism and the vibrational hypothesis of olfaction required the agent to define the chemical scope and computational pathway of each investigation. A graph-construction skill distilled from these studies then enabled coding agents to author typed execution graphs for MOF literature mining. Together, these results show how typed execution graphs turn reusable procedural knowledge into scientific protocols that can be inspected, revised and transferred across computational and physical systems.