aiqbench analysis
SciDER addresses critical gaps in current AI agents by introducing a data-centric, multi-agent framework that autonomously handles the full research lifecycle from hypothesis generation to reproducible code synthesis. The system demonstrates strong performance on benchmarks involving raw data analysis and multimodal visualization, offering a practical step toward democratizing open-source scientific discovery. By releasing both a fine-tuned 27B model and a high-quality execution trajectory dataset, the project provides tangible resources for advancing end-to-end experimental automation.
SciDER: Scientific Data-centric End-to-end Researcher
arXiv:2603.01421v3 Announce Type: replace-cross Abstract: While large language models accelerate scientific discovery, existing agents face severe limitations in adaptability, domain generalization, and multimodal scalability, often struggling to autonomously process raw, domain-specific experimental data. To overcome these barriers, we introduce SciDER, a multi-agent system designed to flexibly automate the entire research lifecycle. This framework employs a novel data-centric approach and integrates a dynamic multimodal skill system across four specialized sub-agents. Specifically, an ideation agent generates novel hypotheses via Evolutionary Idea Search, a data analysis agent systematically structures raw data, an experimentation agent synthesizes executable code grounded in dataset characteristics, and a critic agent drives iterative self-refinement. To democratize open-source scientific discovery, we release OpenSciDER-SFT-8K, a high-quality execution trajectory dataset, alongside the OpenSciDER-27B fine-tuned model. Across six benchmarks, SciDER and OpenSciDER obtain competitive or leading results, with especially strong gains on data-centric analysis, end-to-end research execution, and multimodal scientific visualization. By integrating data analysis with experimental execution, SciDER bridges the gap between abstract scientific reasoning and reproducible experimentation synthesis.
Abstract:While large language models accelerate scientific discovery, existing agents face severe limitations in adaptability, domain generalization, and multimodal scalability, often struggling to autonomously process raw, domain-specific experimental data. To overcome these barriers, we introduce SciDER, a multi-agent system designed to flexibly automate the entire research lifecycle. This framework employs a novel data-centric approach and integrates a dynamic multimodal skill system across four specialized sub-agents. Specifically, an ideation agent generates novel hypotheses via Evolutionary Idea Search, a data analysis agent systematically structures raw data, an experimentation agent synthesizes executable code grounded in dataset characteristics, and a critic agent drives iterative self-refinement. To democratize open-source scientific discovery, we release OpenSciDER-SFT-8K, a high-quality execution trajectory dataset, alongside the OpenSciDER-27B fine-tuned model. Across six benchmarks, SciDER and OpenSciDER obtain competitive or leading results, with especially strong gains on data-centric analysis, end-to-end research execution, and multimodal scientific visualization. By integrating data analysis with experimental execution, SciDER bridges the gap between abstract scientific reasoning and reproducible experimentation synthesis.
Artificial Intelligence (cs.AI); Computation and Language (cs.CL)
arXiv:2603.01421 [cs.AI]
(or arXiv:2603.01421v3 [cs.AI] for this version)
Full text under the publisher's open licence · 177 words
Related coverage
RSIBench-Data: Benchmarking Data-Centric Research for Recursive Self-Improvement
arXiv · Jul 29, 2026
News
Quantum Computing Report · Jun 7, 2026
[AINews] not much happened today
Latent Space · Sep 10, 2026
BRICS Draws a New Global Line: Full Text of New Delhi Declaration
slguardian.org · Sep 12, 2026