This paper demonstrates that Large Language Models (LLMs) can serve as accurate and selective surrogates for costly GPU kernel performance measurements, significantly expanding the search space for op…

OptSkills introduces an archetype-centric skill learning agent that improves the generalization of solving optimization problems from natural language by clustering problems by underlying archetypes a…

The paper introduces a data-centric optimization pipeline to improve coding agents' ability to interact with a branching lakehouse, showing significant accuracy gains by treating agent evaluation as a…

Hawkeye is a system that allows perfect, precision-preserving reproduction of GPU-level matrix multiplication operations on a CPU, enabling efficient and trustworthy third-party auditing of machine le…

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…

MOSAIC is a novel scheduling framework that significantly accelerates Mixture-of-Agents (MoA) workloads by jointly optimizing expert placement and utilizing confidence-aware adaptive aggregation.

The paper introduces Rotary GPU, an exploratory execution approach demonstrating that large Mixture-of-Experts models can be run locally on consumer GPUs with limited VRAM, achieving usable decode thr…

This paper introduces a novel class of backdoor attacks that exploit the numerical side effects of LLM inference optimization, achieving high success rates while maintaining clean accuracy.

Mellum 2 is an open-weight 12B Mixture-of-Experts (MoE) language model specialized for software engineering, achieving performance competitive with larger models while maintaining the efficiency of a…

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 introduces MalSkills, a neuro-symbolic framework that detects malicious skills in the expanding agentic supply chain by analyzing security-sensitive operations across heterogeneous artifacts…

HighTide is an evolving, AI-assisted, open-source benchmark suite for VLSI design, providing a comprehensive and scalable platform for hardware development.

AI-PROPELLER introduces a novel interprocedural code layout optimization system that uses an agentic evolutionary workflow to achieve significant, measurable performance gains in large-scale, real-wor…

The paper demonstrates that using Reinforcement Learning from Verifiable Rewards (RLVR) significantly improves small language models' functional correctness in code generation, particularly when combi…

The paper introduces MASA, a model-aware skill alignment framework that adaptively rewrites general and task-specific skills for LLM agents, achieving superior performance across diverse backbones and…

The paper proposes a trust schema and verification framework to ensure that agent skills, which augment LLMs, are rigorously verified before deployment, thereby making human-in-the-loop oversight scal…

The paper demonstrates the potential of using LLMs within verifier-guided evolutionary coding agents to develop and improve algorithms, specifically applied to contraction order optimization in tensor…

The paper proposes an objective-wise reputation-market mechanism to dynamically calibrate and gate LLM-generated expert priors in multi-objective Bayesian optimization, showing that dynamic calibratio…

BenchEvolver introduces a solution-centric evolutionary framework to automatically transform saturated coding benchmarks into significantly harder, high-quality, and diverse evaluation suites.

The paper introduces BOUNDARY FLOW, an LLVM-based framework that enhances kernel fuzzing and analysis by extracting per-task, state-aware data-flow information (arguments and return values) at functio…