InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
🤖 AI Summary
This work proposes the first unified autonomous agent framework designed to address the challenges of coherence and continuous improvement in long-term, cross-domain scientific discovery. The framework integrates computational modeling and wet-lab experimentation within a closed-loop architecture composed of three synergistic subsystems—generation, validation, and evolution—organized in a modular design. It incorporates deep reasoning, automated optimization, long-term memory, and tight experiment-computation coordination. Evaluated on benchmarks including GAIA, HLE, and GPQA, the system demonstrates state-of-the-art performance and successfully autonomously designs machine learning algorithms. Moreover, it executes end-to-end scientific experiments across Earth science, life sciences, biology, and physics, yielding novel discoveries and showcasing general-purpose, cross-disciplinary autonomous research capabilities.
Application Category
📝 Abstract
We introduce InternAgent-1.5, a unified system designed for end-to-end scientific discovery across computational and empirical domains. The system is built on a structured architecture composed of three coordinated subsystems for generation, verification, and evolution. These subsystems are supported by foundational capabilities for deep research, solution optimization, and long horizon memory. The architecture allows InternAgent-1.5 to operate continuously across extended discovery cycles while maintaining coherent and improving behavior. It also enables the system to coordinate computational modeling and laboratory experimentation within a single unified system. We evaluate InternAgent-1.5 on scientific reasoning benchmarks such as GAIA, HLE, GPQA, and FrontierScience, and the system achieves leading performance that demonstrates strong foundational capabilities. Beyond these benchmarks, we further assess two categories of discovery tasks. In algorithm discovery tasks, InternAgent-1.5 autonomously designs competitive methods for core machine learning problems. In empirical discovery tasks, it executes complete computational or wet lab experiments and produces scientific findings in earth, life, biological, and physical domains. Overall, these results show that InternAgent-1.5 provides a general and scalable framework for autonomous scientific discovery.
Problem
Research questions and friction points this paper is trying to address.
autonomous scientific discovery
long-horizon reasoning
unified agentic framework
computational and empirical domains
end-to-end discovery
Innovation
Methods, ideas, or system contributions that make the work stand out.
agentic framework
long-horizon autonomy
scientific discovery
unified architecture
computational-experimental integration
🔎 Similar Papers
No similar papers found.
