{"ID":5553363,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-02T15:49:53.24596159Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00041","arxiv_id":"2607.00041","title":"ATM: CID-Brokered Pre-Write Admission for Multi-Agent Code Co-Synthesis","abstract":"Multi-agent LLM systems can decompose software-engineering work into planning, generation, validation, and repair, but a narrower systems problem remains: before any governed shared mutation is applied, a system must decide which concurrently formed write intents may proceed in parallel, which require deterministic composition or serialization, and which must take a fail-closed path. We address this problem with the AI-Atomic-Framework (ATM), a specification-grounded governance substrate for software agents operating within a single governance domain. ATM binds task intent, repository scope, write admission, validation, and evidence obligations into one governance chain. A Content Identifier (CID) broker serves as the shared-mutation admission subsystem. Adapter-guided atomization maps write intents to semantic atoms and bounded regions; when persistent atom-map coverage is incomplete, virtual atoms provide temporary auditable governance units for conservative comparison and routing. Governed shared writes are ultimately applied by a neutral steward rather than directly by proposing agents. Evaluation combines controlled, field, adoption, and extension evidence, including a 12-scenario deterministic design matrix, three archived runner cases, ATM-AdmissionBench, three archived same-file boundary cases, a three-week external-adopter study, and an operational recovery-routing benchmark. The results support feasibility, auditability, and bounded recoverability within the observed single-domain settings, but do not claim broad comparative superiority or cross-clone governance.","short_abstract":"Multi-agent LLM systems can decompose software-engineering work into planning, generation, validation, and repair, but a narrower systems problem remains: before any governed shared mutation is applied, a system must decide which concurrently formed write intents may proceed in parallel, which require deterministic com...","url_abs":"https://arxiv.org/abs/2607.00041","url_pdf":"https://arxiv.org/pdf/2607.00041v1","authors":"[\"Eagl Huang\"]","published":"2026-06-29T16:02:38Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.AI\"]","methods":"[\"Large Language Model\"]","has_code":false}