arXiv:2604. 19341v2 Announce Type: replace-cross Abstract: Scientific discovery often requires many cycles of proposing, testing, and refining candidate solutions.
arXiv:2606. 29082v1 Announce Type: cross Abstract: Would experience designing faster GPU kernels also help close in on a long-standing open mathematical conjecture?
The paper investigates Test‑Time Scaling (TTS) for large language models (LLMs) in the context of automated scientific equation discovery, an open‑ended task where models iteratively search candidate equations using observed data for feedback. It frames equation discovery as a unified iterative search that encompasses Best‑of‑N, sequential refinement, tree search, and evolutionary methods, and studies how compute allocation—particularly search width—affects performance under fixed budgets. Experiments on the LLM‑SRBench dataset show that increasing search width with more compute improves results, while other factors like population‑branching split and controller choice have smaller impacts, indicating that controlling exploration versus exploitation is key to scaling LLM‑based equation discovery.
ExplorationBench is a new benchmark designed to evaluate AI systems’ ability to conduct scientific exploration in verifiable alien worlds. It comprises two sandbox environments—AlienCode and AlienLogic—each containing discovery targets, tasks, flawed manuals, and tool‑call schemas that force systems to formulate hypotheses, design experiments, and iterate on results. Ten AI systems were tested, revealing that while the best performers can learn and apply unfamiliar rules, their progress varies across exploration trajectories and can even regress with continued exploration.
ExplorationBench is a benchmark designed to evaluate AI systems’ ability to conduct scientific exploration in verifiable alien worlds, where rules are executable and can be precisely checked. It consists of two sandboxes—AlienCode and AlienLogic—each offering discovery targets, tasks, flawed manuals, environmental feedback, and tool‑call schemas. The benchmark tests whether systems can generate new hypotheses, design experiments, and iterate on results, rather than merely recalling pre‑trained knowledge, and finds that top performers can acquire and apply unfamiliar rules, though performance varies across exploration trajectories.
MOSAIC‑SR is a new symbolic regression method that combines a pretrained Transformer with search‑based refinement. The Transformer generates multiple initial sketches, which seed searches that jointly recover equation structure and constants using scale‑aware optimization and symbolic repair. On the SRSD‑Feynman dataset and six other benchmarks, MOSAIC‑SR achieves the highest symbolic solution rate and ranks among the top two in predictive accuracy, even when irrelevant dummy variables are present.
arXiv:2609.15973v1 Announce Type: new Abstract: Foundation models have progressed from learning and reasoning over existing knowledge, to increasingly learning through action, tool use, and outcome f...
arXiv:2512. 19799v2 Announce Type: replace Abstract: Advances in LLM reasoning and tool use have enabled agentic science, yet frontier theoretical and computational physics remains challenging because research requires deep domain expertise, long-horizon reasoning, and reliable numerical computation.
arXiv:2602. 06448v2 Announce Type: replace-cross Abstract: Large Language Model (LLM)-based scientific agents have accelerated scientific discovery, yet they often suffer from significant inefficiencies due to adherence to fixed initial priors.
Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents helps, but simply adding web search tool can kee...
arXiv:2607. 10127v1 Announce Type: cross Abstract: Evolutionary program search guided by Large Language Models (LLMs) has emerged as a powerful paradigm for automated scientific discovery.
arXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents...
InsightSR is a new framework that integrates Large Language Models (LLMs) with the PySR genetic programming engine to refine symbolic regression search spaces. It employs two LLM-guided pathways: a Semantic Seed Pathway that generates dimensionally consistent functional skeletons, and a Structural Feature Pathway that suggests nonlinear feature transformations. Over successive iterations, these pathways expand the input space and shift the search toward shallow, semantically informed trees, with a feedback loop that evaluates and refines candidate features. The method achieves a 95% exact recovery rate on the Feynman benchmark and 80.18% accuracy on the LLM-SRBench LSR-Transform task, outperforming existing genetic programming and neural-symbolic approaches while preserving strong out-of-distribution generalization.