SCOPE:Planning for Hybrid Querying over Clinical Trial Data

TL;DR

This paper introduces SCOPE, a multi-LLM planning framework that improves reasoning over clinical trial data by explicitly decomposing tasks, leading to better accuracy and efficiency in answering complex questions.

Contribution

The paper presents SCOPE, a novel multi-LLM planner-based approach that explicitly decomposes clinical trial reasoning tasks, outperforming existing methods in accuracy and efficiency.

Findings

Explicit multi-LLM planning improves reasoning accuracy.

SCOPE outperforms zero-shot, few-shot, and other baseline methods.

Hybrid planning offers a better accuracy-efficiency tradeoff.

Abstract

We study clinical trial table reasoning, where answers are not directly stored in visible cells but must be reasoned from semantic understanding through normalization, classification, extraction, or lightweight domain reasoning. Motivated by the observation that current LLM approaches often suffer from "bad reasoning" under implicit planning assumptions, we focus on settings in which the model must recover implicit attributes such as therapy type, added agents, endpoint roles, or follow-up status from partially observed clinical-trial tables. We propose SCOPE (Structured Clinical hybrid Planning for Evidence retrieval in clinical trials), a multi-LLM planner-based framework that decomposes the task into row selection, structured planning, and execution. The planner makes the source field, reasoning rules, and output constraints explicit before answer generation, reducing ambiguity relative to direct prompting. We evaluate SCOPE on 1,500 hybrid reasoning questions over oncology clinical-trial tables against zero-shot, few-shot, chain-of-thought, TableGPT2, Blend-SQL, and EHRAgent. Results show that explicit multi-LLM planning improves accuracy for reasoning-based questions while offering a stronger accuracy-efficiency tradeoff than heavier agentic baselines. Our findings position clinical trial reasoning as a distinct table understanding problem and highlight hybrid planner-based decomposition as an effective solution