Goal-Persistent Coding Agents as Scientific Performance Engineers: A Fixed-Radius Nearest-Neighbor Case Study
cs.AI, cs.PF, cs.SE
Submitted: 2026-09-25
Updated: 2026-09-25
Code: https://github.com/xju2/libFRNN
Terminology
Sources
- Performance of a Geometric Deep Learning Pipeline for HL-LHC Particle Tracking
- Accelerating the Inference of the Exa.TrkX Pipeline
- ReEvo: Large Language Models as Hyper-Heuristics with Reflective Evolution
- AlphaEvolve: A coding agent for scientific and algorithmic discovery
- AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimization
- AVO: Agentic Variation Operators for Autonomous Evolutionary Search
- CudaForge: An Agent Framework with Hardware Feedback for CUDA Kernel Optimization
- KForge: Program Synthesis for Diverse AI Hardware Accelerators
- FormulaCode: Evaluating Agentic Optimization on Large Codebases
- The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search
- Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents
Related papers
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
- MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
- Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems
- VSAL: A Vision Solver with Adaptive Layouts for Graph Property Detection