# A Contract-Centered Architecture for Scalable and Manageable Agentic Runtimes

arXiv: https://arxiv.org/abs/2608.27086 · HTML: https://mlsanity.com/paper/2608.27086/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 18 of its 51 references that are in the map.
- First posted on arXiv 27 Aug 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 18 of 18)

- [MemoHarness: Agent Harnesses That Learn from Experience](https://mlsanity.com/paper/2607.14159/) (2026)
- [Benign in Isolation, Harmful in Composition: Security Risks in Agent Skill Ecosystems](https://mlsanity.com/paper/2606.15242/) (2026)
- [Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable](https://mlsanity.com/paper/2607.13285/) (2026)
- [DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback](https://mlsanity.com/paper/2605.22781/) (2026)
- [Agentic Coding in the Wild: Characterizing GitHub Copilot Traces at Production Scale](https://mlsanity.com/paper/2608.00101/) (2026)
- [From Model Scaling to System Scaling: Scaling the Harness in Agentic AI](https://mlsanity.com/paper/2605.26112/) (2026)
- [Phantom Guardrails: When Self-Improving Agent Harnesses Fix Failures That Never Happened](https://mlsanity.com/paper/2607.13083/) (2026)
- [Do Agent Optimizers Compound? A Continual-Learning Evaluation on Terminal-Bench 2.0](https://mlsanity.com/paper/2607.14004/) (2026)
- [Agent Skill Security: Threat Models, Attacks, Defenses, and Evaluation](https://mlsanity.com/paper/2607.13987/) (2026)
- [Is Progressive Disclosure All You Need for Long-Context Agents?](https://mlsanity.com/paper/2607.17598/) (2026)
- [A Five-Plane Reference Architecture for Runtime Governance of Production AI Agents](https://mlsanity.com/paper/2606.12320/) (2026)
- [SkillCorpus: Consolidating and Evaluating the Open Skill Ecosystem for Real-World LLM Agents](https://mlsanity.com/paper/2607.15557/) (2026)
- [AEVAL: From Anecdotal to Deterministic Testing for Agentic Skill Workflows](https://mlsanity.com/paper/2607.16345/) (2026)
- [Workflow-Localized Mechanism Learning: Attribution-Guided Repair and Knowledge Reuse for Structured Agent Skills](https://mlsanity.com/paper/2607.20999/) (2026)
- [Scoped Verification for Reliable Long-Horizon Agentic Context Evolution under Distribution Shift](https://mlsanity.com/paper/2607.09175/) (2026)
- [Cross-Layer Misalignment Detection in Agent Skills: A Progressive Loading-Aware Contrastive Learning Approach](https://mlsanity.com/paper/2607.10534/) (2026)
- [Falsifiable Release Gates for Self-Improving Systems: Standing Invariants at Scale](https://mlsanity.com/paper/2607.13070/) (2026)
- [Skillware: A Software Ontology and Engineering Lifecycle for Persistent Behavioral Artifacts](https://mlsanity.com/paper/2607.18970/) (2026)

## Abstract (arXiv)

Enterprise agentic systems must coordinate changing capabilities, execution capacity, and independently governed data. We define Skill, Harness, Scaffold, and an external data substrate as responsibility contracts. The central hypothesis, cost-aware capability-capacity separability, asks whether compatible capacity changes preserve semantic outcomes while capability changes preserve the capacity-response relationship within declared margins and enforcement budgets. We operationalize the data boundary through a source-oriented Data Wiki, an output-oriented Theme Wiki, and a versioned Intermediate Relation. Executable 5W1H+Which predicates bind source identity, validity, authorization, semantics, operations, relations, and evidence requirements. Request-bound tickets add execution-time revalidation and typed rejection. A conditional soundness argument states the required trust and atomicity assumptions; dependency invalidation makes change propagation explicit. A single-process reference model agrees with a declared specification oracle on all 1,024 combinations in a finite synthetic fault domain and passes five lifecycle checks. These are conformance results, not measurements of retrieval quality, production safety, or scaling. We specify a held-out data study and a cluster-period crossover with distinct supported, falsified, conditional-engineering, and inconclusive verdicts. The core separability hypothesis remains empirically untested.