An AI-driven closed-loop system autonomously creates in-kernel eBPF Wi-Fi rate controllers that outperform the Minstrel algorithm by 21% in web-page load time and peak throughput on a 58-node testbed.
Let the barbarians in: How AI can accelerate systems performance research
10 Pith papers cite this work. Polarity classification is still indexing.
10
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 10verdicts
UNVERDICTED 10roles
background 2representative citing papers
Jitskit is an iterative LLM-based synthesis pipeline that generates key-value stores matching spec cards for YCSB workloads, resources, and properties, outperforming SOTA baselines on all 18 tested cases by up to 4.6x.
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
AIChilles finds 49 distinct hidden weaknesses across 30 AI-evolved programs in five applications by combining workload extraction, agent-based constraint inference, differential oracles, and coverage to expose regressions.
ScientistOne introduces Chain-of-Evidence and an audit system that achieves zero hallucinated references, perfect score verification, and top method-code alignment while matching or beating human experts on five frontier tasks and generalizing to six more.
AADvark extends agent-aided CAD design to dynamic 3D assemblies with movable parts by integrating constraint solvers and visual feedback to create a verification signal for the agent.
Co-evolving LLM-generated solutions with their evaluators enables discovery of novel database algorithms that outperform state-of-the-art baselines, including a query rewrite policy with up to 6.8x lower latency.
DDS introduces typed contracts at intent, operator DAG, skills, and runtime layers to bound agentic search for data system compositions, achieving convergence on a trading workload where unbounded iteration fails.
LLMs fail at architectural reasoning for networked systems, but Kepler uses structured constraints and SMT-based optimization to synthesize feasible designs with explanations.
Case study applies verifier-guided LLM evolutionary agents to contraction-order optimization in tensor networks and concludes that human validation remains essential.
citing papers explorer
-
IteRate: Autonomous AI Synthesis of In-Kernel eBPF Wi-Fi Rate Control Algorithms
An AI-driven closed-loop system autonomously creates in-kernel eBPF Wi-Fi rate controllers that outperform the Minstrel algorithm by 21% in web-page load time and peak throughput on a 58-node testbed.
-
The Time is Here for Just-in-Time Systems: Challenges and Opportunities
Jitskit is an iterative LLM-based synthesis pipeline that generates key-value stores matching spec cards for YCSB workloads, resources, and properties, outperforming SOTA baselines on all 18 tested cases by up to 4.6x.
-
What Do Evolutionary Coding Agents Evolve?
Evolutionary coding agents achieve most benchmark gains through a small subset of edit types and by cycling previously deleted code lines rather than developing new algorithmic structures.
-
AIChilles: Automatically Uncovering Hidden Weaknesses in AI-Evolved Systems
AIChilles finds 49 distinct hidden weaknesses across 30 AI-evolved programs in five applications by combining workload extraction, agent-based constraint inference, differential oracles, and coverage to expose regressions.
-
ScientistOne: Towards Human-Level Autonomous Research via Chain-of-Evidence
ScientistOne introduces Chain-of-Evidence and an audit system that achieves zero hallucinated references, perfect score verification, and top method-code alignment while matching or beating human experts on five frontier tasks and generalizing to six more.
-
Agent-Aided Design for Dynamic CAD Models
AADvark extends agent-aided CAD design to dynamic 3D assemblies with movable parts by integrating constraint solvers and visual feedback to create a verification signal for the agent.
-
AI-Driven Research for Databases
Co-evolving LLM-generated solutions with their evaluators enables discovery of novel database algorithms that outperform state-of-the-art baselines, including a query rewrite policy with up to 6.8x lower latency.
-
Declarative Data Services: Structured Agentic Discovery for Composing Data Systems
DDS introduces typed contracts at intent, operator DAG, skills, and runtime layers to bound agentic search for data system compositions, achieving convergence on a trading workload where unbounded iteration fails.
-
Assistants, Not Architects: The Role of LLMs in Networked Systems Design
LLMs fail at architectural reasoning for networked systems, but Kepler uses structured constraints and SMT-based optimization to synthesize feasible designs with explanations.
-
Algorithmic algorithm development with LLMs: A Case Study on LLM-Usage for Contraction Order Optimization in Tensor Networks
Case study applies verifier-guided LLM evolutionary agents to contraction-order optimization in tensor networks and concludes that human validation remains essential.