arXiv Machine Learning
Sep 25
A New Gap Sequence for Shellsort: RL-Driven Algorithm Discovery Beyond $N^{4/3}$
arXiv:2609. 29881v1 Announce Type: cross Abstract: Choosing Shellsort gaps is a well-known open problem.
The Program Is Still There: A Conservation Law for Program Discovery
arXiv:2606. 13799v1 Announce Type: cross Abstract: Finding the shortest program that generates a sequence is uncomputable, and for six decades that fact has been mistaken for a wall around finding any generating program.
Related stories
arXiv AI
Jul 17
When a Verified World Model Still Loses: Play-Adequacy vs Prediction-Accuracy in LLM-Synthesized Code World Models
arXiv:2607. 14169v1 Announce Type: new Abstract: Large language models can synthesize a game's rules as executable code - a Code World Model (CWM) - which a classical planner then searches over.
arXiv AI
Aug 7
Relay, Don't Route: Adaptive Population Handoff for Cost-Efficient LLM-Driven Evolution
arXiv:2608. 05651v1 Announce Type: cross Abstract: Large language model (LLM)-driven evolution has shown promise for program search and algorithm discovery, but relying on strong models throughout long evolutionary runs is costly.
arXiv AI
Sep 25
Operator Packages, Proposer Strength, and Construction-Family Plateaus in Office-Scale Verified Search
The paper reports on a large‑scale verified search experiment using a 30B language model on a laptop, evaluating three operator packages—schematic notebooks, named obstacles, and behavioural repulsion—in a factorial design across nine construction problems. Results show that the full composition of operators closes the seed‑to‑record gap more effectively than any single component, increases construction‑hash diversity, and that memory plus repulsion consistently avoids collapse. A frontier proposer achieves similar gains in far fewer samples, but the search ultimately stalls near a plateau where the reference family is adopted and optimized only when provided as code.
arXiv AI
Jun 18
LLM-Evolved Domain-Independent Heuristics for Symbolic AI Planning
arXiv:2605. 29649v2 Announce Type: replace Abstract: Heuristic search is the dominant paradigm in symbolic AI planning, and the strongest heuristics are the result of decades of work by planning researchers.
arXiv AI
3d ago
MILO: Automated Harness Discovery via Orchestrated Multi-Agent Evolution
arXiv:2609.38349v1 Announce Type: cross Abstract: Modern agentic systems combine an AI model with a harness that controls execution and environmental interactions. Harness design strongly affects lon...
arXiv AI
Jun 16
Runtime Analysis of Cartesian Genetic Programming in Evolving Boolean Functions
arXiv:2606. 15923v1 Announce Type: cross Abstract: Cartesian Genetic Programming (CGP) is among the practical and popular forms of Genetic Programming as it uses a graph-based representation of programs.
arXiv AI
Jun 3
Don't Gamble, GAMBLe: An Analytical Framework for AI-Driven Research Systems
arXiv:2606. 02863v1 Announce Type: new Abstract: AI-Driven Research Systems (ADRS) -- systems coupling LLMs with automated evaluation to discover algorithms, proofs, and designs -- are being optimized and adopted across domains, but the tools to analyze them have not kept pace.
arXiv AI
Aug 18
The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach
arXiv:2608. 16438v1 Announce Type: new Abstract: In a world where valuable artifacts are increasingly created, completed, or processed by LLMs, the central economic question is not only what the LLM can produce, but what \emph{value} remains in the inputs (i.
arXiv AI
Sep 24
Combining LLMs and Genetic Search for ARC-AGI-2
The paper presents a hybrid approach that combines large language models (LLMs) with genetic algorithms to solve ARC-AGI-2 tasks. An LLM (Qwen3.5-4B) first generates a small set of programs, which seed a genetic algorithm that evolves these programs within a domain‑specific language ensuring validity. This method yields 6 correct solutions out of 60 tasks (10%), outperforming either technique alone.
arXiv AI
Sep 15
Large Language Models As Shannon Lossy Compressors Not Solomonoff Induction Estimators: The Singularity Is Not Near Without Symbolic Model Synthesis in Program Space
arXiv:2601.05280v4 Announce Type: replace-cross Abstract: On the one hand, the question of whether Large Language Models (LLMs) are Solomonoff induction estimators has become an explicit question at...
arXiv AI
4d ago
Evolving Towards Better Codes: LLM-Guided Search for High-Distance Binary Linear Codes
arXiv:2609.37056v1 Announce Type: cross Abstract: Evolutionary program search driven by large language models (LLMs) has produced record-breaking constructions for open problems in combinatorics and...