SAGA reduces AI agent task completion time by 1.64x on 64-GPU clusters by scheduling at the full workflow level with execution graphs, affinity batching, and completion-time fairness.
Title resolution pending
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
years
2026 3verdicts
UNVERDICTED 3representative citing papers
Homogeneous multi-agent debate introduces sycophantic conformity, contextual fragility, and consensus collapse, leading to equal or lower accuracy than isolated self-correction at 2.1-3.4x higher token cost on GSM-Hard and MMLU-Hard.
Analysis of bugs in modern agentic frameworks uncovers unique symptoms like unexpected execution sequences and root causes including model faults and orchestration issues, with transferable patterns across designs.
citing papers explorer
-
SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
SAGA reduces AI agent task completion time by 1.64x on 64-GPU clusters by scheduling at the full workflow level with execution graphs, affinity batching, and completion-time fairness.
-
The Cost of Consensus: Isolated Self-Correction Prevails Over Unguided Homogeneous Multi-Agent Debate
Homogeneous multi-agent debate introduces sycophantic conformity, contextual fragility, and consensus collapse, leading to equal or lower accuracy than isolated self-correction at 2.1-3.4x higher token cost on GSM-Hard and MMLU-Hard.
-
Dissecting Bug Triggers and Failure Modes in Modern Agentic Frameworks: An Empirical Study
Analysis of bugs in modern agentic frameworks uncovers unique symptoms like unexpected execution sequences and root causes including model faults and orchestration issues, with transferable patterns across designs.