# MatClaw: An Autonomous Code-First LLM Agent for End-to-End Materials Exploration

arXiv: https://arxiv.org/abs/2604.02688 · HTML: https://mlsanity.com/paper/2604.02688/

## 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 14 of its 31 references that are in the map.
- First posted on arXiv 3 Apr 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, 14 of 14)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Lost in the Middle: How Language Models Use Long Contexts](https://mlsanity.com/paper/2307.03172/) (2023)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Efficient Streaming Language Models with Attention Sinks](https://mlsanity.com/paper/2309.17453/) (2023)
- [ChemCrow: Augmenting large-language models with chemistry tools](https://mlsanity.com/paper/2304.05376/) (2023)
- [DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics](https://mlsanity.com/paper/1712.03641/) (2017)
- [The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management](https://mlsanity.com/paper/2508.21433/) (2025)
- [El Agente: An Autonomous Agent for Quantum Chemistry](https://mlsanity.com/paper/2505.02484/) (2025)
- [cAST: Enhancing Code Retrieval-Augmented Generation with Structural Chunking via Abstract Syntax Tree](https://mlsanity.com/paper/2506.15655/) (2025)
- [Agent-based Learning of Materials Datasets from Scientific Literature](https://mlsanity.com/paper/2312.11690/) (2023)
- [TopoMAS: Large Language Model Driven Topological Materials Multiagent System](https://mlsanity.com/paper/2507.04053/) (2025)
- [VASP Agent: An Agentic Framework for Autonomous First-principles Calculations](https://mlsanity.com/paper/2512.19458/) (2025)

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

- [Socratic agents for autonomous scientific discovery in high-dimensional physical systems](https://mlsanity.com/paper/2606.26722/) (2026)
- [OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics Research](https://mlsanity.com/paper/2605.13618/) (2026)
- [Science Done on a Machine by a Machine: AI Agents in Computational Chemistry](https://mlsanity.com/paper/2608.18508/) (2026)
- [CompMat-Bench: Benchmarking AI Agents for Computational Materials Science](https://mlsanity.com/paper/2610.00636/) (2026)

## Abstract (arXiv)

Existing LLM agents for computational materials science are constrained by pipeline-bounded architectures tied to specific simulation codes and by dependence on manually written tool functions that grow with task scope. We present MatClaw, a code-first agent that writes and executes Python directly, composing any installed domain library to orchestrate multi-code workflows on remote HPC clusters without predefined tool functions. To sustain coherent execution across multi-day workflows, MatClaw uses a four-layer memory architecture that prevents progressive context loss, and retrieval-augmented generation over domain source code that raises per-step API-call accuracy to ~99 %. Three end-to-end demonstrations on ferroelectric CuInP2S6 (machine-learning force field training via active learning, Curie temperature prediction, and heuristic parameter-space search) reveal that the agent handles code generation reliably but struggles with tacit domain knowledge. The missing knowledge, such as appropriate simulation timescales, equilibration protocols, and sampling strategies, is the kind that researchers accumulate through experience but rarely formalize. Two lightweight interventions, literature self-learning and expert-specified constraints, bridge these gaps, defining a guided autonomy model in which the researcher provides high-level domain knowledge while the agent handles workflow execution. Our results demonstrate that the gap between guided and fully autonomous computational materials research is narrower than ever before: LLMs already handle code generation and scientific interpretation reliably, and the rapid improvement in their capabilities will accelerate materials discovery beyond what manual workflows can achieve. All code and benchmarks are open-source.