InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery
Abstract
InternAgent-1.5 is a unified system for autonomous scientific discovery that integrates computational modeling and experimental research through coordinated subsystems for generation, verification, and evolution.
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.
Community
Proposes InternAgent-1.5, a unified, three-subsystem agent for end-to-end long-horizon scientific discovery with memory, verification, and evolution across computation and experiments.
This is an automated message from the Librarian Bot. I found the following papers similar to this paper.
The following papers were recommended by the Semantic Scholar API
- Accelerating Scientific Discovery with Autonomous Goal-evolving Agents (2025)
- Probing Scientific General Intelligence of LLMs with Scientist-Aligned Workflows (2025)
- Toward Ultra-Long-Horizon Agentic Science: Cognitive Accumulation for Machine Learning Engineering (2026)
- Can We Predict Before Executing Machine Learning Agents? (2026)
- InfiAgent: An Infinite-Horizon Framework for General-Purpose Autonomous Agents (2026)
- Rethinking the AI Scientist: Interactive Multi-Agent Workflows for Scientific Discovery (2026)
- Towards AGI A Pragmatic Approach Towards Self Evolving Agent (2026)
Please give a thumbs up to this comment if you found it helpful!
If you want recommendations for any Paper on Hugging Face checkout this Space
You can directly ask Librarian Bot for paper recommendations by tagging it in a comment:
@librarian-bot
recommend
Excited to share InternAgent 1.5 a unified system for cross-disciplinary scientific discovery! ๐
The system features three core subsystems (Generation, Validation, Evolution) with innovations in deep research, solution refinement, and long-term persistence.
As shown in the benchmarks, we achieve leading performance across GAIA (86.06), GPQA (87.37), HLE, and FrontierScience. Unlike existing systems, InternAgent 1.5 is the only one supporting both algorithm & empirical discovery with full capabilities including wet lab and persistence running.
InternAgent1.5 is validated in biology, earth science, and material science - compressing traditional workflows from weeks to minutes. Welcome to check our technical report and share feedback! โญ๐
Models citing this paper 0
No model linking this paper
Datasets citing this paper 0
No dataset linking this paper
Spaces citing this paper 0
No Space linking this paper