Search papers, labs, and topics across Lattice.
ResearchEVO is introduced as an end-to-end framework that automates scientific discovery by first evolving algorithms through LLM-guided co-evolution, and then generating publication-ready research papers using retrieval-augmented generation with anti-hallucination techniques. The framework was validated on quantum error correction and physics-informed neural networks, discovering novel, human-interpretable algorithmic mechanisms in both domains. The system then autonomously generated LaTeX manuscripts that correctly grounded these discoveries in existing theory without fabricating citations.
Forget months of manual experimentation: ResearchEVO autonomously discovers and documents novel scientific algorithms, even generating the LaTeX paper.
An important recurring pattern in scientific breakthroughs is a two-stage process: an initial phase of undirected experimentation that yields an unexpected finding, followed by a retrospective phase that explains why the finding works and situates it within existing theory. We present ResearchEVO, an end-to-end framework that computationally instantiates this discover-then-explain paradigm. The Evolution Phase employs LLM-guided bi-dimensional co-evolution -- simultaneously optimizing both algorithmic logic and overall architecture -- to search the space of code implementations purely by fitness, without requiring any understanding of the solutions it produces. The Writing Phase then takes the best-performing algorithm and autonomously generates a complete, publication-ready research paper through sentence-level retrieval-augmented generation with explicit anti-hallucination verification and automated experiment design. To our knowledge, ResearchEVO is the first system to cover this full pipeline end to end: no prior work jointly performs principled algorithm evolution and literature-grounded scientific documentation. We validate the framework on two cross-disciplinary scientific problems -- Quantum Error Correction using real Google quantum hardware data, and Physics-Informed Neural Networks -- where the Evolution Phase discovered human-interpretable algorithmic mechanisms that had not been previously proposed in the respective domain literatures. In both cases, the Writing Phase autonomously produced compilable LaTeX manuscripts that correctly grounded these blind discoveries in existing theory via RAG, with zero fabricated citations.