BioDisco: Multi-agent hypothesis generation with dual-mode evidence, iterative feedback and temporal evaluation
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.
Code (0)
등록된 구현이 없습니다.
Tasks
Knowledge GraphsSimilar Papers 제목 키워드 기반
BioDiscoveryAgent: An AI Agent for Designing Genetic Perturbation Experiments
Agents based on large language models have shown great potential in accelerating scientific discovery by leveraging their rich background knowledge and reasoning capabilities. In this paper, we introduce BioDiscoveryAgen…
AI AgentBayesian Optimizationscientific discoveryA new multi-metric approach for quantifying global biodiscovery and conservation priorities reveals overlooked hotspots for amphibians
Undocumented species represent one of the largest hurdles for conservation efforts due to the uncertainty they introduce into conservation planning. Until the distribution of earth's biodiversity is better understood, su…
HypoAgent: An Agentic Framework for Interactive Abductive Hypothesis Generation over Knowledge Graphs
Abductive reasoning over knowledge graphs aims to generate logical hypotheses that explain observed entities or facts. Existing controllable hypothesis generation methods allow users to guide this process with explicit c…
Semantic SimilarityIntent RecognitionKnowledge GraphsHypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
Scientific agents contribute to hypothesis discovery by synthesizing evidence, assessing proposals, and developing new explanations. Recent systems combine scientific agents with evolutionary search through critique, com…
MAGIS: Evidence-Based Multi-Agent Reasoning for Interpretable Strabismus Clinical Decision-Making
Strabismus is a common ocular disorder that requires fine-grained subtype diagnosis for individualized treatment planning. However, existing deep learning methods mainly provide diagnostic predictions without transparent…