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.

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.

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…

This paper proposes using offline reinforcement learning (RL) as an efficient alternative to online RL for post-training code-generating LLMs, demonstrating its effectiveness, especially for smaller m…

The paper introduces CHECKMATE, a novel framework that uses code evolution to automatically generate and optimize algorithms for complex combinatorial problems, outperforming state-of-the-art solvers.

The paper proposes CoEvo-AHD, an LLM-driven co-evolutionary framework that co-evolves two coupled operator populations to design effective heuristics for combinatorial optimization problems with stron…

The paper introduces Opt-Verifier, a novel LLM-based framework that significantly improves the accuracy of automated optimization model generation by implementing dual-side verification from both stru…

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…

The paper experimentally evaluates 12 multi-agent LLM collaboration topologies for software design, finding that structural adversarial prompting and cross-model review are the most effective approach…

The paper empirically and theoretically demonstrates that incorporating Lamarckian and Baldwinian mechanisms into evolutionary algorithms significantly outperforms standard Darwinian evolution, especi…

The paper proposes a modular agent framework and novel learning methods to design and optimize practical, cost-effective, and controllable LLM-based agentic systems.

The paper introduces OR-Space, a novel full-lifecycle workspace benchmark designed to rigorously evaluate industrial optimization agents by simulating real-world, multi-stage OR workflows that go beyo…

KLineage introduces a novel method to teach LLMs when and how to apply GPU kernel optimizations by reverse-engineering expert kernel lineages, resulting in superior optimization skills compared to exi…

The paper introduces an LLM-guided evolutionary workflow that successfully discovers and certifies a large number of novel bivariate quantum error-correcting codes, demonstrating the utility of LLMs i…

FPMoE introduces a sparse Mixture-of-Experts (MoE) architecture to improve functional code generation across multiple functional programming languages, achieving state-of-the-art performance with fewe…

The paper introduces a novel LLM-driven evolutionary framework to synthesize admissible, domain-specific pattern generators, enabling optimal classical planning with high performance and interpretabil…

The paper proposes Meta-Team, an experience-driven framework that enables multi-agent systems (MAS) to collaboratively self-evolve by transforming complex execution experiences into reusable improveme…

The paper proposes Multi-Order Communication (MOC) to overcome the limitations of standard first-order message passing in LLM-based multi-agent systems, significantly improving performance by capturin…

The study found that while multi-agent LLM code generation architectures significantly affect code complexity, the added complexity does not translate into better functional correctness, suggesting ar…