Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test
Agent harnesses combine retrieval, routing, state, provenance, and verification, but locally successful components may disagree on shared state. We model this failure with a finite \emph{capability sheaf}: stalks encode typed behavior signatures, restriction maps retain shared fields, and accepted runs are useful global sections. An exact finite constraint-satisfaction problem (CSP) defines acceptance, while a linearized relative cohomology class provides a diagnostic and search feature. A contr
Record details
Published: 13 August 2026
Source: arXiv
Category: Research
Topics: Healthcare · Agents & autonomy
Retrieved: 14 August 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.
MARC v1: An Open-Source Multi-Agent Framework for Clinical AI Reasoning and Coordination
arXiv cs.AI · 13 August 2026
Unmasking Toxic Mimicry in Medical Offline Reinforcement Learning for ICU Sepsis Management via Counterfactual Clinical Audits
arXiv cs.CY · 13 August 2026
Why Do AI Agents Break Rules? How Framing, Context, and Social Signals Shape Compliance
arXiv cs.CY · 14 August 2026
CTBench: Evaluating Troubleshooting Capabilities of AI Agents in Realistic Telecom Network Operations
arXiv cs.AI · 12 August 2026
MIRA: Medical Image Reflection for Agentic Diagnosis
arXiv cs.AI · 11 August 2026
Avalon-ToM-Bench: Evaluating Fine-Grained Theory of Mind via Asymmetric Game Mechanics
arXiv cs.AI · 10 August 2026
How to cite this record
ethics.ai (13 August 2026), “Capability Sheaves for Compositional Agent-Harness Repair: Controlled Quotients and a Real-Repository Stress Test,” evidence record 19177, https://ethics.ai/record/19177 (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.