HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
- URL: http://arxiv.org/abs/2609.15938v1
- Date: Mon, 14 Sep 2026 17:44:49 GMT
- Title: HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses
- Abstract summary: How different forms of agent collaboration affect hypothesis quality remains an open question.<n>We introduce HypoEvolve, which makes collaboration explicit through successive updates to a hypothesis population.<n>Each generation specifies how scientific judgments and new proposals reshape the population, making collaboration effects on hypothesis quality directly testable.
- Score: 35.57672494910454
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: 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, comparison, and revision. However, how different forms of agent collaboration affect hypothesis quality remains an open question. Answering this question requires separating the effects of agents' scientific capabilities from those of their collaboration. A framework must therefore preserve agents' scientific roles and support rules for combining, revising, and retaining hypotheses. Building on this view, we introduce HypoEvolve, which makes collaboration explicit through successive updates to a hypothesis population. Specifically, we propose a generational genetic algorithm to coordinate specialized large language model (LLM) agents that integrate mechanistic arguments, reconsider assumptions, and assess evidence and testability. Each generation specifies how scientific judgments and new proposals reshape the population, making collaboration effects on hypothesis quality directly testable. Moreover, we design our evaluation around scientifically meaningful hypotheses that explain how a proposed intervention could work. Drug repurposing links these explanations to target-level biological claims assessed against external evidence. Specifically, we adapt DepMap and Open Targets into complementary external measures grounded in experimental, genetic, and clinical evidence. Across 34 cancer types, HypoEvolve achieves the highest scores against six baselines on both measures. DepMap selectivity reaches 0.171, versus 0.115 for the strongest baseline. Gains over single-pass generation also generalize to held-out cancer types. HypoEvolve advances a vision of autonomous science in which AI research teams achieve a capacity for discovery beyond that of individual models.
Related papers
- EvoSCM: Scientific Belief Revision Through Causal Model Evolution and Experimentation [68.80901568810616]
EvoSCM aims to equip scientific agents with explicit structural causal models that evolve as new evidence is collected.<n>We evaluate EvoSCM onPhysics, a benchmark requiring agents to uncover the hidden dynamics of noncanonical physical worlds through experimentation.
arXiv Detail & Related papers (2026-09-01T16:55:56Z) - Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents [0.42970700836450476]
Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery.<n>Here we propose the Hypothesis Evolution Protocol (HEP), an agent harness that provides hypothesis generation, evaluation, and evolution as explicit, auditable operations.<n>On materials-science research tasks, a HEP-equipped agent operates the hypothesis--test--evidence--belief cycle that planning-style agents lack, generalizes across research questions, and exploits the protocol more fully as the base LLM becomes more capable.
arXiv Detail & Related papers (2026-07-10T08:39:30Z) - HypoAgent: An Agentic Framework for Interactive Abductive Hypothesis Generation over Knowledge Graphs [52.91976391891331]
Abductive reasoning over knowledge graphs aims to generate logical hypotheses that explain observed entities or facts.<n>Existing controllable hypothesis generation methods allow users to guide this process with explicit conditions.<n>We propose HypoAgent, an Agentic framework for interactive abductive Hypothesis Generation over knowledge graphs.
arXiv Detail & Related papers (2026-05-29T14:40:37Z) - Hypothesis Hunting with Evolving Networks of Autonomous Scientific Agents [52.50038914857797]
We term this process hypothesis hunting: the cumulative search for insight through sustained exploration across vast and complex hypothesis spaces.<n>We introduce AScience, a framework modeling discovery as the interaction of agents, networks, and evaluation norms, and implement it as ASCollab.<n> Experiments show that such social dynamics enable the accumulation of expert-rated results along the diversity-quality-novelty frontier.
arXiv Detail & Related papers (2025-10-08T08:47:07Z) - Bayes-Entropy Collaborative Driven Agents for Research Hypotheses Generation and Optimization [4.469102316542763]
This paper proposes a multi-agent collaborative framework called HypoAgents.<n>It generates hypotheses through diversity sampling and establishes prior beliefs.<n>It then employs etrieval-augmented generation (RAG) to gather external literature evidence.<n>It identifies high-uncertainty hypotheses using information entropy $H = - sum p_ilog p_i$ and actively refines them.
arXiv Detail & Related papers (2025-08-03T13:05:32Z) - Towards an AI co-scientist [48.11351101913404]
We introduce an AI co-scientist, a multi-agent system built on Gemini 2.0.<n>The AI co-scientist is intended to help uncover new, original knowledge and to formulate demonstrably novel research hypotheses.<n>The system's design incorporates a generate, debate, and evolve approach to hypothesis generation, inspired by the scientific method.
arXiv Detail & Related papers (2025-02-26T06:17:13Z) - BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery [32.395366135636046]
We introduce BoxingGym, a benchmark with 10 environments for evaluating experimental design and model discovery.<n>We compute the expected information gain (EIG), an information-theoretic quantity which measures how much an experiment reduces uncertainty about the parameters of a generative model.<n>We find that current LLMs, such as GPT-4o, struggle with both experimental design and model discovery.
arXiv Detail & Related papers (2025-01-02T21:15:57Z) - Large Language Models for Automated Open-domain Scientific Hypotheses Discovery [50.40483334131271]
This work proposes the first dataset for social science academic hypotheses discovery.
Unlike previous settings, the new dataset requires (1) using open-domain data (raw web corpus) as observations; and (2) proposing hypotheses even new to humanity.
A multi- module framework is developed for the task, including three different feedback mechanisms to boost performance.
arXiv Detail & Related papers (2023-09-06T05:19:41Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.