The paper investigates how the set of prior iterates influences success in large language model (LLM)-driven discovery tasks. It introduces 12 new harnesses called 'Modular' and evaluates them on five diverse discovery problems, revealing that success is fragile and highly dependent on harness design. The study identifies mode collapse—a sharp loss of iterate diversity—as a common failure, and shows that early discoveries predict final outcomes, leading to a new initialization strategy that consistently improves performance across harnesses and applications.
arXiv:2606. 11256v1 Announce Type: cross Abstract: Designing molecules with target properties is most useful when candidate structures are accompanied by feasible synthetic routes.
arXiv:2610.00675v1 Announce Type: cross Abstract: Evolutionary approaches to LLM-driven discovery often generate new programs from a small set of selected ancestors. This keeps contexts manageable bu...
arXiv:2606. 26728v1 Announce Type: new Abstract: Scientific discovery is fundamentally an optimization problem, defined by a vast "state space" of theories and experiments, and an evaluation criterion based on quality, novelty, and validity.
arXiv:2606. 10587v1 Announce Type: cross Abstract: Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses.
arXiv:2602.00663v3 Announce Type: replace Abstract: Optimizing molecules to achieve desired properties is a central bottleneck across the chemical sciences, particularly in the pharmaceutical industr...
arXiv:2604. 19341v2 Announce Type: replace-cross Abstract: Scientific discovery often requires many cycles of proposing, testing, and refining candidate solutions.
The paper explores how large language models (LLMs) can be trained for small-molecule drug design by using synthetic tasks that are cheaper to evaluate. By employing a curriculum that gradually increases task difficulty, the authors demonstrate that LLMs can learn design strategies that outperform larger models on structure-based lead optimization. This approach shows that scaling post‑training with synthetic tasks can effectively adapt LLMs to high‑cost experimental scenarios that are otherwise infeasible to train on directly.
arXiv:2607. 08393v1 Announce Type: new Abstract: Fine-tuning LLMs to inject new knowledge faces a critical challenge: LLMs can quickly memorize new facts, yet fail to use them for downstream reasoning tasks.
arXiv:2608. 15669v1 Announce Type: new Abstract: Scientific discovery often involves optimising expensive-to-evaluate objectives over vast, structured, and open-ended hypothesis spaces, such as molecules, protein sequences, and computer programs.
EvoTreeNAD is a genealogy‑guided evolutionary algorithm that autonomously discovers neural architectures without a predefined seed or search space. Starting from an empty root, it builds a persistent genealogy where each node represents a complete architecture; top‑percentile values from nodes and descendants steer lineage selection. The method combines an Idea Agent that proposes variants and a Code Agent that implements them, with theoretical analysis showing stationary variation regimes and empirical results demonstrating superior performance on CIFAR‑10/100 and MedMNIST‑v2 tasks.
arXiv:2609.36187v1 Announce Type: new Abstract: Symbolic Regression (SR) is a data-driven method for scientific discovery which searches for interpretable analytical relationships within data. Recent...
The paper introduces PACEvolve, a framework that improves self‑evolving agents powered by Large Language Models by addressing their tendency to become trapped in local contexts and repeat flawed hypotheses. It does so through three techniques: Hierarchical Context Management to prune memory, Momentum‑Based Backtracking to escape local minima, and a self‑adaptive Collaborative Evolution policy to balance refinement and knowledge transfer. These methods enable the agents to maintain a global view of search momentum and achieve state‑of‑the‑art results on complex evolutionary benchmarks.