Toward Auditable AI Scientists: A Hypothesis Evolution Protocol for LLM Agents
2026-07-10 • Artificial Intelligence
Artificial Intelligence
AI summaryⓘ
The authors created a system called the Hypothesis Evolution Protocol (HEP) to help AI language models work more clearly and logically when solving science problems. Instead of hiding their thinking process in messy logs, the AI using HEP shows each step of making and testing guesses, so scientists can follow and check its work. They tested this on materials science tasks and found it helps AI reason better and adapt as the AI itself improves. This work is a move toward AI scientists whose reasoning is easy to inspect and trust.
large language modelshypothesis testingscientific discoveryauditable AImaterials sciencereasoning cyclebelief updateAI agentsprotocolplanning agents
Authors
Izumi Takahara, Teruyasu Mizoguchi
Abstract
Large language model (LLM) agents are increasingly expected to play a central role in AI-driven scientific discovery. Equipped with broad knowledge, flexible reasoning, and tool use, they have the potential to autonomously explore and solve scientific problems by repeatedly proposing hypotheses, testing them, and revising their beliefs in the light of the evidence. In current agents, however, these hypotheses, tests, and belief updates are buried in unstructured logs, and no mechanism lets the agent or the human researcher audit that process. Here we propose the Hypothesis Evolution Protocol (HEP), an agent harness that provides hypothesis generation, evaluation, and evolution as explicit, auditable operations. 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. These results mark a step toward auditable AI scientists, whose scientific reasoning can be inspected, verified, and built upon.