The year/Independent research

Paper 2602.08990

InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery

Published
Feb 2026
Research lab
Independent
Citations
20
GitHub
1.4K stars

01 In brief

Summary

InternAgent-1.5 is a unified agentic framework for long-horizon autonomous scientific discovery, developed by the InternScience Team at Shanghai Artificial Intelligence Laboratory.

It addresses limitations of existing AI Scientist systems, such as domain-specific designs and limited long-horizon operation, by integrating three coordinated subsystems: Generation, Verification, and Evolution.

These are supported by foundational capabilities for deep research, solution refinement, and long-horizon memory.

The system achieves leading performance on benchmarks including GAIA (86.06%), HLE (40.87% text-only), GPQA-diamond (87.37%), and FrontierScience (77.20% Olympiad).

In algorithm discovery, it outperforms baselines across six scientific tasks (e.g., AutoRYP R² 36.6, AutoEAP HK-PCC 0.91) and four AI algorithm tasks (e.g., AutoTTS 72.5, AutoLM 0.904).

In empirical discovery, it autonomously executes workflows in earth science (climate downscaling RMSE 0.8488), life science (reproducing GPR160 and ARG2 target discoveries), biological science (fluorescent protein engineering), and physical science (reaction prediction Top-1 0.86).

The structured cognitive memory (SPM, TEM, SKM) is shown to improve planning efficiency, adaptation, and long-term knowledge accumulation.

02 From the paper

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.