# AUTOCT: Automating Interpretable Clinical Trial Prediction with LLM Agents

arXiv: https://arxiv.org/abs/2506.04293 · HTML: https://mlsanity.com/paper/2506.04293/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 34 references that are in the map.
- First posted on arXiv 4 Jun 2025.

## Builds on (most cited first, 16 of 16)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs](https://mlsanity.com/paper/2306.13063/) (2023)
- [Understanding the planning of LLM agents: A survey](https://mlsanity.com/paper/2402.02716/) (2024)
- [Large Language Models for Generative Information Extraction: A Survey](https://mlsanity.com/paper/2312.17617/) (2023)
- [A Survey of LLM-based Agents in Medicine: How far are we from Baymax?](https://mlsanity.com/paper/2502.11211/) (2025)
- [Large Language Models Can Automatically Engineer Features for Few-Shot Tabular Learning](https://mlsanity.com/paper/2404.09491/) (2024)
- [HINT: Hierarchical Interaction Network for Trial Outcome Prediction Leveraging Web Data](https://mlsanity.com/paper/2102.04252/) (2021)
- [COMPOSE: Cross-Modal Pseudo-Siamese Network for Patient Trial Matching](https://mlsanity.com/paper/2006.08765/) (2020)
- [ClinicalAgent: Clinical Trial Multi-Agent System with Large Language Model-based Reasoning](https://mlsanity.com/paper/2404.14777/) (2024)
- [Exploring Large Language Models for Feature Selection: A Data-centric Perspective](https://mlsanity.com/paper/2408.12025/) (2024)
- [Deceptive Semantic Shortcuts on Reasoning Chains: How Far Can Models Go without Hallucination?](https://mlsanity.com/paper/2311.09702/) (2023)
- [Conceptual and Unbiased Reasoning in Language Models](https://mlsanity.com/paper/2404.00205/) (2024)
- [SPOT: Sequential Predictive Modeling of Clinical Trial Outcome with Meta-Learning](https://mlsanity.com/paper/2304.05352/) (2023)
- [Adaptive Reasoning and Acting in Medical Language Agents](https://mlsanity.com/paper/2410.10020/) (2024)

## Built on by (most cited first, 9 of 9)

- [Autonomous Research Agents: A Survey of AI Scientists and the Verification Gap](https://mlsanity.com/paper/2608.05179/) (2026)
- [A Survey on LLM-Assisted Clinical Trial Recruitment](https://mlsanity.com/paper/2506.15301/) (2025)
- [Formalize, Don't Optimize: The Heuristic Trap in LLM-Generated Combinatorial Solvers](https://mlsanity.com/paper/2605.12421/) (2026)
- [ClinicalReTrial: Clinical Trial Redesign with Self-Evolving Agents](https://mlsanity.com/paper/2601.00290/) (2026)
- [Agentic AI in Healthcare & Medicine: A Seven-Dimensional Taxonomy for Empirical Evaluation of LLM-based Agents](https://mlsanity.com/paper/2602.04813/) (2026)
- [Aligning Clinical Needs and AI Capabilities: A Survey on LLMs for Medical Reasoning](https://mlsanity.com/paper/2607.07761/) (2026)
- [Evaluating Agentic Bioinformatics through Function, Evidence, and Validation](https://mlsanity.com/paper/2607.27556/) (2026)
- [When Do Corrective Features Help? An Agent for Corrective Feature Discovery on Black-Box Forecasters](https://mlsanity.com/paper/2608.05207/) (2026)
- [TrialAtlas: Multi-Agent Research Organization for Clinical Trial Design and Optimization](https://mlsanity.com/paper/2609.21859/) (2026)

## Abstract (arXiv)

Clinical trials are critical for advancing medical treatments but remain prohibitively expensive and time-consuming. Accurate prediction of clinical trial outcomes can significantly reduce research and development costs and accelerate drug discovery. While recent deep learning models have shown promise by leveraging unstructured data, their black-box nature, lack of interpretability, and vulnerability to label leakage limit their practical use in high-stakes biomedical contexts. In this work, we propose AutoCT, a novel framework that combines the reasoning capabilities of large language models with the explainability of classical machine learning. AutoCT autonomously generates, evaluates, and refines tabular features based on public information without human input. Our method uses Monte Carlo Tree Search to iteratively optimize predictive performance. Experimental results show that AutoCT performs on par with or better than SOTA methods on clinical trial prediction tasks within only a limited number of self-refinement iterations, establishing a new paradigm for scalable, interpretable, and cost-efficient clinical trial prediction.