Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
Sherlock: Reliable and Efficient Agentic Workflow Execu- tion
6 Pith papers cite this work. Polarity classification is still indexing.
6
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
years
2026 6roles
background 2polarities
background 2representative citing papers
ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
SAGA introduces workflow-atomic scheduling for compound AI agents, achieving 1.64x lower task completion time and 1.22x better memory utilization than vLLM on a 64-GPU cluster at the cost of 30% lower peak throughput.
A four-primitive agent runtime layer between agent frameworks and LLM serving engines raises cross-session KV-cache hit rate by 13–37 percentage points in the paper's experiments.
BaseRT achieves up to 1.56x higher LLM decode throughput than llama.cpp on Apple Silicon through native Metal kernel fusion and unified memory optimizations.
Position paper advocating a shift from on-the-fly AI agent synthesis to reusable hardened workflows in an AI Workflow Store to improve robustness and security.
citing papers explorer
-
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement
Models delayed verification in multi-agent LLMs as graph consensus, derives stability thresholds (inverse golden ratio for delay two) via grounded Laplacian, and gives a supermodular greedy rule for corrector placement; experiments on five models confirm dose-delay oscillations.
-
ASAP: Agent-System Co-Design for Wall-Clock-Centered Auto HPO Research for ML Experiments
ASAP integrates an LLM agent over a pool of HPO tools and adds system-level optimizations (prefix-stable prompts, speculation parallelism, Self-Tuner) to improve end-to-end wall-clock performance on diverse HPO tasks.
-
SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
SAGA introduces workflow-atomic scheduling for compound AI agents, achieving 1.64x lower task completion time and 1.22x better memory utilization than vLLM on a 64-GPU cluster at the cost of 30% lower peak throughput.
-
A Policy-Driven Runtime Layer for Agentic LLM Serving
A four-primitive agent runtime layer between agent frameworks and LLM serving engines raises cross-session KV-cache hit rate by 13–37 percentage points in the paper's experiments.
-
BaseRT: Best-in-Class LLM Inference on Apple Silicon via Native Metal
BaseRT achieves up to 1.56x higher LLM decode throughput than llama.cpp on Apple Silicon through native Metal kernel fusion and unified memory optimizations.
-
Engineering Robustness into Personal Agents with the AI Workflow Store
Position paper advocating a shift from on-the-fly AI agent synthesis to reusable hardened workflows in an AI Workflow Store to improve robustness and security.