Scientific Hypothesis Generation

Overview

Scientific hypothesis generation studies how to turn prior knowledge and observations into testable explanations, research questions, or predictions. Common approaches use literature retrieval and knowledge graphs to connect concepts, while multi-agent debate, evolutionary search, and reinforcement learning generate and refine candidate ideas; experimental systems also select new measurements to test them. Evaluation increasingly examines grounding, novelty, feasibility, and whether hypotheses predict evidence held back from the system, using expert review, benchmarks, and real-world validation. A central tension is that fluent, seemingly novel proposals may lack mechanistic support, while reliable evaluation is difficult and current systems still need human scrutiny and experimental feedback.

Latest papers

94 papers5 papers in the last four weeks, down 64% on the four weeks before. 0.0% of all new papers.

Mar 4, 2026

MOOSE-Star: Unlocking Tractable Training for Scientific Discovery by Breaking the Complexity Barrier

While large language models (LLMs) show promise in scientific discovery, existing research focuses on inference or feedback-driven training, leaving the direct modeling of the generative reasoning process, P(hypothesis∣background)P(\text{hypothesis}|\text{background}) (P(h∣b)P(h|b)), unexplored. We demonstrate that directly training P(h∣b)P(h|b) is mathematically intractable due to the combinatorial complexity (O(Nk)O(N^k)) inherent in retrieving and composing inspirations from a vast knowledge base. To break this barrier, we introduce MOOSE-Star, a unified framework that enables tractable and scalable training of P(h∣b)P(h|b), while supporting more scalable inference. In the best case, MOOSE-Star reduces complexity from exponential to logarithmic (O(log⁡N)O(\log N)) by (1) training on decomposed subtasks derived from the probabilistic equation of discovery, (2) employing motivation-guided hierarchical search to enable logarithmic retrieval and prune irrelevant subspaces, and (3) utilizing bounded composition for robustness against retrieval noise. To facilitate this, we release TOMATO-Star, a dataset of 108,717 decomposed papers (38,400 GPU hours) for training. Empirically, MOOSE-Star scales continuously with training data and inference budget, whereas direct brute-force sampling hits a complexity wall.
Feb 28, 2026

From Literature to Hypotheses: An AI Co-Scientist System for Biomarker-Guided Drug Combination Hypothesis Generation

The rapid growth of biomedical evidence makes it difficult to translate biomarker mechanisms into actionable drug combination hypotheses. We present CoDHy, an interactive AI co-scientist for biomarker-guided hypothesis generation in oncology. CoDHy constructs task-specific knowledge graphs from curated databases and biomedical literature, then combines graph embeddings with agent-based reasoning to generate, validate, and rank evidence-grounded drug combinations. Through a web interface, researchers specify the biomarker, cancer context, and literature scope; inspect supporting evidence and intermediate results; and iteratively refine the generated hypotheses. The demonstration presents CoDHy's end-to-end workflow and shows how researchers can interactively explore and compare mechanistically supported drug combinations while remaining in control of hypothesis prioritization.
Feb 26, 2025

Accelerating scientific discovery with Co-Scientist

Scientific discovery is driven by scientists generating novel hypotheses for complex problems that undergo rigorous experimental validation. To augment this process, we introduce Co-Scientist, a multi-agent AI system built on Gemini for structured scientific thinking and hypothesis generation. Co-Scientist aims to help scientists discover new original knowledge. Conditioned on their research objectives and prior scientific evidence, it formulates demonstrably novel research hypotheses for experimental verification. The system's design involves agents continuously generating, critiquing and refining hypotheses accelerated by scaling test-time compute. Key contributions include: (1) a multi-agent architecture with an asynchronous task execution framework for flexible compute scaling; (2) a tournament evolution process for self-improving hypotheses generation. Automated evaluations show continued benefits of test-time compute scaling, improving hypothesis quality over time. While general purpose, we focus the validation in three biomedical applications: drug repurposing, novel target discovery, and explaining mechanisms of anti-microbial resistance. Specifically, Co-Scientist helped identify new drug repurposing candidates and synergistic combination therapies for acute myeloid leukemia, which were validated through in vitro experiments. These real-world validations demonstrate the potential of Co-Scientist to accelerate scientific discovery and usher in an era of AI empowered scientists.
May 27, 2024

Generating Interesting Scientific Ideas using Knowledge Graphs and LLMs: Evaluations with 100 Research Group Leaders

The rapid growth of scientific literature makes it increasingly challenging for researchers to identify novel and impactful ideas, especially across disciplines. Modern artificial intelligence (AI) systems offer new opportunities for scientific ideation, but how compelling are AI-generated ideas, and how can their quality be improved? Here, we introduce SciMuse, which generates personalized research ideas using a knowledge graph of 58 million papers and a large language model (LLM). A central focus of this work is to understand how interesting these ideas are. Therefore, we conducted a large-scale evaluation in which more than 100 research group leaders -- spanning the natural sciences to the humanities -- rated over 4,400 personalized ideas according to their level of interest. Overall, expert ratings were modest (mean 2.40 on a 5-point scale, most common rating 1), while 24.9% of ideas were rated 4 or 5. We find that supplying concept pairs selected using the knowledge graph does not improve expert-rated interest over a titles-only GPT baseline. High-citation-predicted pairs even showed a weak tendency (1.94σσ) toward lower interest than random pairs. Nevertheless, graph features can be used to control properties of ideas, and, using this unique evaluation dataset, we show that idea interest can be predicted with both a supervised neural network based on graph features and a zero-shot ranking approach based on an LLM. Our work provides an AI methodology for generating scientific ideas and a large-scale interdisciplinary expert evaluation, paving the way to study and improve difficult-to-measure metrics such as expert-perceived scientific interestingness.