HypoEvolve: Genetic Algorithms Enable Multi-Agent LLMs to Discover Scientific Hypotheses

arXiv:2609.15938 · cs.CL, cs.CE, cs.MA, cs.NE · Submitted 2026-09-14 · Read on arXiv

cs.CL, cs.CE, cs.MA, cs.NE

Submitted: 2026-09-14

Updated: 2026-09-14

Comments: 22 pages, 8 figures, 5 tables

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Consistency — 6× in this paper · explained in 3 episodes
• Self-consistency — 6× in this paper · explained in 2 episodes
• Core — 4× in this paper · explained in 2 episodes
• Ablation — 3× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 2 episodes
• Large Language Model (LLM) — 2× in this paper · explained in 3 episodes
• Multi-Agent System — 2× in this paper · explained in 6 episodes
• Pairwise Comparisons — 2× in this paper · explained in 2 episodes
• Provenance — 2× in this paper · explained in 4 episodes
• Adaptation — 1× in this paper · explained in 1 episode
• Aggregation — 1× in this paper · explained in 1 episode
• Bradley-Terry model — 1× in this paper · explained in 2 episodes
• Iterative Refinement — 1× in this paper · explained in 3 episodes
• Knowledge Graph — 1× in this paper · explained in 7 episodes
• Knowledge graphs — 1× in this paper · explained in 2 episodes
• LLM-as-a-Judge — 1× in this paper · explained in 3 episodes
• Large Language Models (LLMs) — 1× in this paper · explained in 6 episodes
• Multi-Agent Framework — 1× in this paper · explained in 3 episodes
• World Model — 1× in this paper · explained in 7 episodes

Sources

• Multi-Agent Evolve: LLM Self-Improve through Co-evolution
• TritonDFT: Automating DFT with a Multi-Agent Framework
• AlphaEvolve: A coding agent for scientific and algorithmic discovery
• Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
• CellMaster: Collaborative Cell Type Annotation in Single-Cell Analysis
• The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search

Related papers

• Exploring Solution Divergence and Its Effect on Large Language Model Problem Solving
• Ishigaki-IDS-Bench: A Benchmark for Generating Information Delivery Specification from BIM Information Requirements
• Subliminal Steering: Stronger Encoding of Hidden Signals
• MedStruct-S: A Benchmark for Key Discovery, Key-Conditioned QA and Semi-Structured Extraction from OCR Clinical Reports
• The End of Transformers? On Challenging Attention and the Rise of Sub-Quadratic Architectures
• Untangling the Mechanisms of Misleading Context in Medical Question Answering