# HALO: Interactive Co-abductive Reasoning in Scientific Hypothesis Generation

arXiv: https://arxiv.org/abs/2607.18564 · HTML: https://mlsanity.com/paper/2607.18564/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Clinical and biomedical applications, one of 17 directions in LLM reasoning.
- Builds on 7 of its 117 references that are in the map.
- First posted on arXiv 20 Jul 2026.

## Placed in

- LLM reasoning / [Clinical and biomedical applications](https://mlsanity.com/lr/clinical-and-biomedical-applications/)

## Builds on (most cited first, 7 of 7)

- [DiffDock: Diffusion Steps, Twists, and Turns for Molecular Docking](https://mlsanity.com/paper/2210.01776/) (2022)
- [Hypothesis Generation with Large Language Models](https://mlsanity.com/paper/2404.04326/) (2024)
- [Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation](https://mlsanity.com/paper/2407.08940/) (2024)
- [Sparks of Science: Hypothesis Generation Using Structured Paper Data](https://mlsanity.com/paper/2504.12976/) (2025)
- [A Survey on Hypothesis Generation for Scientific Discovery in the Era of Large Language Models](https://mlsanity.com/paper/2504.05496/) (2025)
- [GeLLMO: Generalizing Large Language Models for Multi-property Molecule Optimization](https://mlsanity.com/paper/2502.13398/) (2025)
- [Accelerating Scientific Discovery with Multi-Document Summarization of Impact-Ranked Papers](https://mlsanity.com/paper/2508.03962/) (2025)

## Abstract (arXiv)

Scientific discovery is essential yet inefficient, primarily because generating hypotheses within a vast search space hinders breakthroughs. While current AI systems assist in generating new hypothesis candidates, they lack interactive support for the reasoning process by which users develop these outputs into promising hypotheses, resulting in surface-level hypotheses. To address this issue, we present co-abduction, a human-AI collaborative framework for abductive reasoning in scientific hypothesis generation. To operationalize co-abduction, we build HALO, a human-AI collaborative system for molecular hypothesis generation in drug discovery, enabling improved candidate clustering, strategy identification, and multi-strategy synthesis. In expert studies involving 10 medicinal chemists, HALO significantly facilitated abductive reasoning for hypothesis generation -- efficient candidate observation, systematic strategy identification, and coherent multi-strategy composition -- and enabled participants to produce higher-quality, more diverse candidate molecules.