Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines
A multi-agent pipeline with N agents typically issues N LLM calls per run. Merging agents into fewer calls (compound execution) promises token savings, but naively merged calls silently degrade quality through tool loss and prompt compression. We present Agent Capsules, an adaptive execution runtime that treats multi-agent pipeline execution as an optimization problem with empirical quality constraints. The runtime instruments coordination overhead per group, scores composition opportunity, sele
Record details
Published: 1 May 2026
Source: arXiv
Category: Research
Topics: Agents & autonomy
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning
arXiv · 1 May 2026
Group Cognition Learning: Making Everything Better Through Governed Two-Stage Agents Collaboration
arXiv · 1 May 2026
Safeguarding LLM Agents from Misalignment through Provenance Analysis
arXiv · 1 May 2026
SAGA: Workflow-Atomic Scheduling for AI Agent Inference on GPU Clusters
arXiv · 1 May 2026
Essential, Yet Overlooked: Identity Verification Barriers for Blind and Low Vision People in Government Services
arXiv · 30 April 2026
AgenticAITA: A Proof-Of-Concept About Deliberative Multi-Agent Reasoning for Autonomous Trading Systems
arXiv · 1 May 2026
How to cite this record
ethics.ai (1 May 2026), “Agent Capsules: Quality-Gated Granularity Control for Multi-Agent LLM Pipelines,” evidence record 5129, https://ethics.ai/record/5129 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.