BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917101236649984 |
|---|---|
| author | Ke, Yujing George, Kevin Pandya, Kathan Blumenthal, David Sprang, Maximilian Großmann, Gerrit Vollmer, Sebastian Selby, David Antony |
| author_facet | Ke, Yujing George, Kevin Pandya, Kathan Blumenthal, David Sprang, Maximilian Großmann, Gerrit Vollmer, Sebastian Selby, David Antony |
| contents | Identifying novel hypotheses is essential to scientific research, yet this process risks being overwhelmed by the sheer volume and complexity of available information. Existing automated methods often struggle to generate novel and evidence-grounded hypotheses, lack robust iterative refinement and rarely undergo rigorous temporal evaluation for future discovery potential. To address this, we propose BioDisco, a multi-agent framework that draws upon language model-based reasoning and a dual-mode evidence system (biomedical knowledge graphs and automated literature retrieval) for grounded novelty, integrates an internal scoring and feedback loop for iterative refinement, and validates performance through pioneering temporal and human evaluations and a Bradley-Terry paired comparison model to provide statistically-grounded assessment. Our evaluations demonstrate superior novelty and significance over ablated configurations and generalist biomedical agents. Designed for flexibility and modularity, BioDisco allows seamless integration of custom language models or knowledge graphs, and can be run with just a few lines of code. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_01285 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation Ke, Yujing George, Kevin Pandya, Kathan Blumenthal, David Sprang, Maximilian Großmann, Gerrit Vollmer, Sebastian Selby, David Antony Artificial Intelligence Information Retrieval Applications Identifying novel hypotheses is essential to scientific research, yet this process risks being overwhelmed by the sheer volume and complexity of available information. Existing automated methods often struggle to generate novel and evidence-grounded hypotheses, lack robust iterative refinement and rarely undergo rigorous temporal evaluation for future discovery potential. To address this, we propose BioDisco, a multi-agent framework that draws upon language model-based reasoning and a dual-mode evidence system (biomedical knowledge graphs and automated literature retrieval) for grounded novelty, integrates an internal scoring and feedback loop for iterative refinement, and validates performance through pioneering temporal and human evaluations and a Bradley-Terry paired comparison model to provide statistically-grounded assessment. Our evaluations demonstrate superior novelty and significance over ablated configurations and generalist biomedical agents. Designed for flexibility and modularity, BioDisco allows seamless integration of custom language models or knowledge graphs, and can be run with just a few lines of code. |
| title | BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation |
| topic | Artificial Intelligence Information Retrieval Applications |
| url | https://arxiv.org/abs/2508.01285 |