From Agent Output to Authorized Transition
On the map: LLM agents and tool use → Software engineering coding agents
Abstract (arXiv)
Agentic engineering systems can edit repositories, run tools and tests, build firmware, synthesize schematics, and prepare deployable or manufacturable artifacts. The assurance problem is therefore shifting from whether an agent can produce an output to whether an engineering lifecycle is justified in acting on claims about that output. Current products and standards provide sandboxes, approvals, hooks, traces, policy enforcement, attestations, bills of materials, and assurance representations, but these capabilities remain fragmented. This paper presents the Agile-V Assurance Spine, a cross-domain transition contract for software, firmware, and PCB engineering. Evidence is admitted only when it establishes required properties through an authoritative source profile, is bound to the exact artifact and frozen policy baseline, remains current with respect to declared dependencies, and satisfies risk-appropriate independence and authority. Gate decisions are recorded as receipts; approvals and exceptions are exact-scope and time-bounded; and authorization is rechecked at the effect boundary before merge, deployment, flashing, release, or fabrication. A bounded review of contemporary research, commercial platforms, open-source infrastructure, and standards positions the model relative to evidence-gated lifecycle control, continuous assurance, runtime admission, provenance, and AI/ML inventories. The paper contributes a precise vocabulary, compositional architecture, domain profiles, mapping to open-source implementations, and an adversarial evaluation agenda. It does not claim regulatory conformity or demonstrated production superiority.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use. Builds on 20 of its 62 references that are in the map. First posted on arXiv 23 Sep 2026.
Builds on
20 of 62 references.
Closest ancestors · 5
Same direction, newest first
- 2026SWE-Bench Pro Verified: A Reliable Benchmark for Software Engineering Agents8 Sep
- 2026Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle4 Sep
- 2026Graphectory Viewer: A Tool for Process-Centric Analysis of Agentic Software Trajectories17 Aug
- 2026Cheap Code, Costly Judgment: A Case Study on Governable Agentic Software Engineering1 Jul
- 2026Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development19 May
Other references · 15
- 2023Identifying the Risks of LM Agents with an LM-Emulated Sandboxcited by 514
- 2026Runtime Governance for AI Agents: Policies on Pathscited by 17
- 2026CIBER: A Comprehensive Benchmark for Security Evaluation of Code Interpreter Agentscited by 5
- 2026Deontic Policies for Runtime Governance of Agentic AI Systemscited by 5
- 2026AgentSecBench: Measuring Prompt Injection, Privacy Leakage, and Tool-Use Integrity in LLM Agentscited by 4
- 2026Proof-or-Stop: Don't Trust the Agent, Trust the Evidence -- Loop Engineering for Verifiable Evidence-Gated Lifecycle Controlcited by 4
- 2026DEMM-Bench: A Cross-Regime Benchmark for Agent-Runtime Governance-Evidence Sufficiencycited by 3
- 2026Verifiable Manifest Signing and Transparency Enforcement for Secure MCP-Based LLM Pipelinescited by 2
- 2026Toward Safe LLM Agents: A Survey of Specification, Verification, and Enforcementcited by 2
- 2026Cognitive Admission Control: Risk-Conditioned Assurance for Consequential Actions in Agentic Distributed Systemscited by 2
- 2026Trustworthy AI Posture (TAIP): A Framework for Continuous AI Assurance of Agentic Systems at Horizontal and Vertical scalecited by 1
- 2026Decision Evidence Maturity Model for Agentic AI: A Property-Level Method Specificationcited by 1
3 more
- 2026pcbGPT: Automatic PCB Schematic Synthesis from Natural Language Requirementscited by 1
- 2026Agent-Integrated Software: Interaction Contracts and Continuous Assurancecited by 1
- 2026AI-GRACE: A Use-Case Operationalization Framework for Agentic AI: From Organizational Objectives and Obligations to Deployment Capabilities and Architecturecited by 1
Built on by
Not cited yet.
Similar, not cited
Close in wording, no citation either way
- 2026From Traceability to Justifiability: Accountability Structures in Agentic Software Engineering
- 2026Trust Is Not a Score: Runtime Assurance Contracts for High-Risk AI Agents
- 2026Model-Based Agentic Software Engineering
- 2026Beyond Component Testing: Validating Agentic AI Systems
- 2026SBOMs into Agentic AIBOMs: Schema Extensions, Agentic Orchestration, and Reproducibility Evaluation
- 2026Beyond Task Success: An Evidence-Synthesis Framework for Evaluating, Governing, and Orchestrating Agentic AI
- 2026Reality Is the Final Verifier: On Two Key Gaps in Agentic Software Engineering
- 2026Assurance Envelopes for Autonomous Coding Agents: Minimum-Cost Evidence for Software Change