Tag
EvoPINN is an agentic framework that reformulates PINN development as an execution-grounded algorithm discovery problem, using an LLM agent to propose programmatic modifications. It autonomously discovers PDE-specialized learning algorithms, including a novel architecture called SLRC-PINN, which outperforms baselines across diverse PDE regimes.
Introduces AgentNAS, a mechanism that uses an LLM to generate a seed architecture and decompose it into a slotted architecture, defining a task-specific search space for conventional NAS to explore, achieving state-of-the-art on 11 of 17 tasks.
This paper proposes formalizing scientific discovery as a meta-optimization problem where LLMs generate and aggregate objective functions via correlation-weighted voting, applied to 3-SAT algorithm discovery using digital MemComputing, achieving a 67x speedup on large instances.
This paper presents Delta-Star, a deep reinforcement learning approach using AlphaZero-style self-play to discover superior lattice reduction strategies by interacting with the primitive actions of the LLL algorithm. The learned policy generalizes to higher dimensions and unseen moduli without retraining.
MLEvolve is a self-evolving LLM-based multi-agent framework for automated ML algorithm discovery that extends tree search to Progressive MCGS with graph-based cross-branch information flow and retrospective memory. It achieves state-of-the-art performance on MLE-Bench and outperforms AlphaEvolve on mathematical algorithm optimization tasks.
This paper trains a small one-layer encoder-decoder transformer on the zeta map bijection for Dyck paths and uses mechanistic interpretability to extract a new explicit algorithm called the scaffolding map, demonstrating an AI-assisted approach to mathematical discovery.
Researchers introduce 'Unlearn-and-Reinvent', a pipeline that removes knowledge of foundational algorithms (e.g., Dijkstra's, Euclid's) from LLMs via unlearning, then tests whether models can independently reinvent them. Results show LLMs can reinvent algorithms with intuitive structures but struggle with those requiring non-obvious data structures or counterintuitive invariants.