Modern Software Engineering with Verification Agents: A Spec-First Architecture for Autonomous Synthesis, Verification IRs, and Organizational Scale
Jason Hickey
Abstract
When autonomous coding agents synthesize implementation code, formal specifications, and mechanical proofs simultaneously, the software engineering hierarchy inverts: the formal specification becomes the primary human-reviewed artifact, while source code and proof scripts become disposable build outputs. This paper presents an end-to-end architecture for agent-authored, formally verified software engineering. First, we establish a logic-agnostic foundation combining a spec-first stack inversion, a zero-code-review workflow gated by automated continuous integration (CI) checks, and a minimal Verification Intermediate Representation (VIR) lowered via a thin, verified translator. Second, we pair an extensional Computational Type Theory (CTT) specification layer with Higher-Order Abstract Syntax (HOAS) and linear resource typing in the VIR--eliminating rewrite friction for synthesis agents while defining an experiment, its protocol frozen before the first reader, to measure whether removing boundary coercions improves human specification readability. Third, we scale collaboration across multi-team organizations using Personal Spec-Copilots and a Shared Synthesis Fleet that detects cross-team Semantic Merge Conflicts and fuses modular contracts into zero-copy binaries. We illustrate this architecture on a zero-copy authenticated message router and distinguish our existing empirical baselines (salt, SaltBench, x86lean, and MetaPRL) from newly proposed components.
Create a lesson
Related papers
Are We Just Applying LLMs? What SE Research Studies, Underexplores, and Could Do Next in the LLM Era
Zeinadsadat Saghi, Sadra Sabouri, Souti Chattopadhyay
Testing Processor Contracts in Speculative Decoding Engines
Tianyu Ding, Yaocheng Tong, Muzhi Yang et al.
Supporting Viewpoint Coordination for Compliance by Design with an Artifact Model for Regulatory Requirements Engineering
Oleksandr Kosenkov, Davide Fucci, Michael Unterkalmsteiner et al.
DistDebug-Bench: Can LLM Agents Diagnose Bugs in Distributed Systems?
Yuxuan Jiang, Chenglin Liu, John Rose et al.
uTECH Turbo-MOVES: The Intersection of Software Architectural Innovation and Sustainable Mobility Analysis
Cafer Avcı, Alireza Yazdiani, Roopak Srinivasan et al.
Specification-Driven Governance for Fairness-by-Design in Agentic Software Engineering: How Far Can We Go?
Alfonso Cannavale, Alessandra Parziale, Valeria Pontillo et al.