End-to-end autonomous scientific discovery on a real optical platform

2026-04-29

AI Summary

This work transcends the conventional role of AI as a mere assistant within predefined scientific workflows by achieving, for the first time, end-to-end autonomous scientific discovery in a real physical system. The authors introduce the Qiushi Discovery Engine—a large language model–based agent system featuring nonlinear research-stage modeling, a Meta-Trace memory mechanism, and a dual-layer architecture—that autonomously executes a complete scientific cycle on a real optical platform, from hypothesis generation and experimental design to validation. The system successfully reproduces transmission matrix experiments, observes coherent-order structures for the first time, and—through 145.9 million tokens and over a thousand physical experiments—independently discovers and verifies a novel nontrivial physical mechanism: optical bilinear interaction, analogous to the core attention operation in Transformers. This breakthrough opens new avenues for efficient optical computing hardware.

Abstract

Scientific research has long been human-led, driving new knowledge and transformative technologies through the continual revision of questions, methods and claims as evidence accumulates. Although large language model (LLM)-based agents are beginning to move beyond assisting predefined research workflows, none has yet demonstrated end-to-end autonomous discovery in a real physical system that produces a nontrivial result supported by experimental evidence. Here we introduce Qiushi Discovery Engine, an LLM-based agentic system for end-to-end autonomous scientific discovery on a real optical platform. Qiushi Engine combines nonlinear research phases, Meta-Trace memory and a dual-layer architecture to maintain adaptive and stable research trajectories across long-horizon investigations involving thousands of LLM-mediated reasoning, measurement and revision actions. It autonomously reproduces a published transmission-matrix experiment on a non-original platform and converts an abstract coherence-order theory into experimental observables, providing, to our knowledge, the first observation of this class of coherence-order structure. More importantly, in an open-ended study involving 145.9 million tokens, 3,242 LLM calls, 1,242 tool calls, 163 research notes and 44 scripts, Qiushi Engine proposes and experimentally validates optical bilinear interaction, a physical mechanism structurally analogous to a core operation in Transformer attention. This AI-discovered mechanism suggests a route towards high-speed, energy-efficient optical hardware for pairwise computation. To our knowledge, this is the first demonstration of an AI agentic system autonomously identifying and experimentally validating a nontrivial, previously unreported physical mechanism, marking a milestone for research-level autonomous agents.

Problem

• autonomous scientific discovery
• real physical system
• nontrivial physical mechanism
• end-to-end autonomy
• experimental validation

Innovation

• autonomous scientific discovery
• LLM-based agent
• optical bilinear interaction
• end-to-end experimentation
• Meta-Trace memory