Tag
DiscoPER is an autonomous framework leveraging large language models and dynamic code generation for open-ended scientific research, using second-order meta-reflection to synthesize discoveries and statistical testing for rigor. Evaluated on a multimodal ecological benchmark, it outperforms baselines in recovering known patterns.
Introduces AHOIS, a multi-agent AI scientist that embeds Socratic midwifery into closed-loop experimentation for epistemic autonomy, enabling autonomous hypothesis construction, testing, and revision in high-dimensional physical systems as demonstrated on a multimode-fibre optical platform.
Tsinghua team proposes EurekAgent, arguing that the bottleneck in autonomous scientific research is environment engineering rather than smarter Agents. By engineering four dimensions—permissions, artifacts, budgets, and human-AI collaboration—they achieve SOTA on several mathematical and kernel engineering tasks, discovering a new optimal arrangement for 26 circles for under $11.
The paper introduces EurekAgent, an environment-engineered agent system for metric-driven autonomous scientific discovery that achieves state-of-the-art results on math, kernel engineering, and ML tasks with low computational costs.