# AutoLabs: Cognitive Multi-Agent Systems with Self-Correction for Autonomous Chemical Experimentation

arXiv: https://arxiv.org/abs/2509.25651 · HTML: https://mlsanity.com/paper/2509.25651/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 43 of its 106 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 30 of 43)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [WizardLM: Empowering large pre-trained language models to follow complex instructions](https://mlsanity.com/paper/2304.12244/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [A Survey on RAG Meeting LLMs: Towards Retrieval-Augmented Large Language Models](https://mlsanity.com/paper/2405.06211/) (2024)
- [ChatGPT for Robotics: Design Principles and Model Abilities](https://mlsanity.com/paper/2306.17582/) (2023)
- [Towards Revealing the Mystery behind Chain of Thought: A Theoretical Perspective](https://mlsanity.com/paper/2305.15408/) (2023)
- [LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models](https://mlsanity.com/paper/2310.05736/) (2023)
- [GPT4Tools: Teaching Large Language Model to Use Tools via Self-instruction](https://mlsanity.com/paper/2305.18752/) (2023)
- [Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents](https://mlsanity.com/paper/2403.02502/) (2024)
- [AI Agents vs. Agentic AI: A Conceptual Taxonomy, Applications and Challenges](https://mlsanity.com/paper/2505.10468/) (2025)
- [EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction](https://mlsanity.com/paper/2401.06201/) (2024)
- [Emergent autonomous scientific research capabilities of large language models](https://mlsanity.com/paper/2304.05332/) (2023)
- [The Prompt Report: A Systematic Survey of Prompt Engineering Techniques](https://mlsanity.com/paper/2406.06608/) (2024)
- [Competitive Programming with Large Reasoning Models](https://mlsanity.com/paper/2502.06807/) (2025)
- [Meta-Prompting: Enhancing Language Models with Task-Agnostic Scaffolding](https://mlsanity.com/paper/2401.12954/) (2024)
- [Large Language Models for Automated Open-domain Scientific Hypotheses Discovery](https://mlsanity.com/paper/2309.02726/) (2023)
- [SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning](https://mlsanity.com/paper/2409.05556/) (2024)
- [Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions](https://mlsanity.com/paper/2503.08979/) (2025)
- [A Survey of Reasoning with Foundation Models](https://mlsanity.com/paper/2312.11562/) (2023)
- [ORGANA: A Robotic Assistant for Automated Chemistry Experimentation and Characterization](https://mlsanity.com/paper/2401.06949/) (2024)
- [KnowAgent: Knowledge-Augmented Planning for LLM-Based Agents](https://mlsanity.com/paper/2403.03101/) (2024)
- [InternAgent: When Agent Becomes the Scientist -- Building Closed-Loop System from Hypothesis to Verification](https://mlsanity.com/paper/2505.16938/) (2025)
- [Scientists' First Exam: Probing Cognitive Abilities of MLLM via Perception, Understanding, and Reasoning](https://mlsanity.com/paper/2506.10521/) (2025)
- [Chemist-X: Large Language Model-empowered Agent for Reaction Condition Recommendation in Chemical Synthesis](https://mlsanity.com/paper/2311.10776/) (2023)

## Built on by (most cited first, 15 of 15)

- [MLS-Bench: A Holistic and Rigorous Assessment of AI Systems on Building Better AI](https://mlsanity.com/paper/2605.08678/) (2026)
- [A Survey of AI Scientists](https://mlsanity.com/paper/2510.23045/) (2025)
- [AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery](https://mlsanity.com/paper/2605.23204/) (2026)
- [Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation](https://mlsanity.com/paper/2510.15624/) (2025)
- [Principle-Evolvable Scientific Discovery via Uncertainty Minimization](https://mlsanity.com/paper/2602.06448/) (2026)
- [Agentic LLM Reasoning in a Self-Driving Laboratory for Air-Sensitive Lithium Halide Spinel Conductors](https://mlsanity.com/paper/2604.11957/) (2026)
- [Towards Agentic Intelligence for Materials Science](https://mlsanity.com/paper/2602.00169/) (2026)
- [HLER: Human-in-the-Loop Economic Research via Multi-Agent Pipelines for Empirical Discovery](https://mlsanity.com/paper/2603.07444/) (2026)
- [PeroMAS: A Multi-agent System of Perovskite Material Discovery](https://mlsanity.com/paper/2602.13312/) (2026)
- [BioProAgent: Neuro-Symbolic Grounding for Constrained Scientific Planning](https://mlsanity.com/paper/2603.00876/) (2026)
- [Agentic Discovery of Non-Canonical Antimicrobial Peptides with AMPGAN v3](https://mlsanity.com/paper/2606.17127/) (2026)
- [Beyond Fixed Representations: The Vocabulary and Verifier Gaps in Open-Ended AI](https://mlsanity.com/paper/2607.09560/) (2026)
- [ChemWorld: Programmable Chemical Worlds for Controlled and Replayable Agent Experimentation](https://mlsanity.com/paper/2608.10792/) (2026)
- [Molecular LLM Agents: From Architectural Design to Scientific Autonomy](https://mlsanity.com/paper/2608.23104/) (2026)
- [Collaborative Principle Evolution via Evidence Transfer for Scientific Discovery](https://mlsanity.com/paper/2609.35315/) (2026)

## Abstract (arXiv)

The automation of chemical research through self-driving laboratories (SDLs) promises to accelerate scientific discovery, yet the reliability and granular performance of the underlying AI agents remain critical, under-examined challenges. In this work, we introduce AutoLabs, a self-correcting, multi-agent architecture designed to autonomously translate natural-language instructions into executable protocols for a high-throughput liquid handler. The system engages users in dialogue, decomposes experimental goals into discrete tasks for specialized agents, performs tool-assisted stoichiometric calculations, and iteratively self-corrects its output before generating a hardware-ready file. We present a comprehensive evaluation framework featuring five benchmark experiments of increasing complexity, from simple sample preparation to multi-plate timed syntheses. Through a systematic ablation study of 20 agent configurations, we assess the impact of reasoning capacity, architectural design (single- vs. multi-agent), tool use, and self-correction mechanisms. Our results demonstrate that agent reasoning capacity is the most critical factor for success, reducing quantitative errors in chemical amounts (nRMSE) by over 85% in complex tasks. When combined with a multi-agent architecture and iterative self-correction, AutoLabs achieves near-expert procedural accuracy (F1-score > 0.89) on challenging multi-step syntheses. These findings establish a clear blueprint for developing robust and trustworthy AI partners for autonomous laboratories, highlighting the synergistic effects of modular design, advanced reasoning, and self-correction to ensure both performance and reliability in high-stakes scientific applications. Code: https://github.com/pnnl/autolabs