EvoGens is an evolution-inspired framework that treats scientific idea generation as an evolutionary search, significantly boosting the novelty and diversity of generated research ideas compared to ex…

The paper proposes a category-theoretic framework for agentic AI that models scientific discovery not as answer generation, but as a verifiable transition and revision of the underlying representation…

MLEvolve is a novel self-evolving multi-agent framework that enables LLM agents to discover and optimize machine learning algorithms for complex, long-horizon tasks.

MOOSE-Copilot is a novel web-based framework that unifies scientific hypothesis discovery by formalizing human-AI interaction, significantly improving performance over autonomous LLM baselines.

The paper advocates for the establishment of Model Science, a systematic discipline that moves beyond simple benchmarking to deeply analyze AI models' internal workings and failure modes.

This paper proposes a multifactorial evolutionary algorithm with collaborative discovery (MFEA-CoD) for multitask novelty search, which coordinates multiple tasks to collaboratively discover novel sol…

The paper introduces IdeaGene-Bench, a benchmark for scientific lineage reasoning and idea generation, which includes 1,961 golden lineage traces, 1,085 curated Idea Genome objects, and 920 pairwise G…

This paper analyzes the performance and explainability requirements of evolutionary algorithms when applied to complex, real-world physics-informed optimization problems, identifying a gap between cur…

This paper investigates the benefits of generating multiple solutions in each generation for Evolutionary Diversity Optimisation (EDO) and proposes efficient methods to achieve it.

This paper proposes an evolutionary framework for discovering developmental reward schedules in reinforcement learning, using three motivational components: agency, novelty, and reactivity.

This paper introduces the first LLM-generated, domain-independent heuristics for symbolic AI planning, using evolutionary search to surpass the performance of hand-engineered state-of-the-art methods.

PaperPilot is an interactive literature search agent that constructs an executable DAG of paper-search operators based on user queries and feedback, improving search results and reducing errors.

The paper introduces Science Earth, a planet-scale scientific runtime that enables diverse, siloed AI capabilities to connect and collaborate dynamically, demonstrating that scientific discovery can b…

This paper develops a convergence theory and runtime bound for closed-loop generative selection in computational drug discovery, showing that elitism makes the search absorbing and proving almost-sure…

The paper proposes BaSE, a multi-armed bandit approach, to optimally allocate a fixed budget of LLM calls across parallel evolutionary search trajectories, significantly improving mean fitness and rel…

The paper introduces AIBuildAI-2, a knowledge-enhanced agent that significantly improves the automatic building of AI models by integrating an external, evolving knowledge system, achieving state-of-t…

The paper introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…

This paper compares the effect of different initialization methods on the accuracy and complexity of solutions in genetic programming for symbolic regression, finding no significant differences.