{"ID":6620460,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T03:28:55.185153975Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.12301","arxiv_id":"2607.12301","title":"XScientist: A Git-Like Research Protocol for Long-Running Autonomous Scientific Discovery","abstract":"Autonomous research systems are often evaluated as one-shot paper generators: given a topic, they produce a manuscript and a small set of experiment logs. This framing hides the operational problem that makes such systems difficult to trust: research is long-running, branching, failure-prone, and dependent on auditable handoffs between agents and humans. XScientist is a git-like research protocol and operating system for this setting. It orchestrates idea generation, experiment execution, manuscript drafting, self-review, repair, quality gating, daemon scheduling, and reproducibility artifacts as one continuously observable pipeline. The central design choice is to treat each run as a portable research artifact rather than only as a PDF. XScientist exports an Agent-Native Research Artifact (ARA), a protocol that records an exploration DAG, per-node code and outputs, claim-to-evidence anchors, content hashes, provenance, and re-execution hooks. This makes each generated paper inspectable as a science exploration tree: failed branches, repaired experiments, ablations, and manuscript claims remain connected to the nodes that produced them. The system also includes deterministic integrity forensics, sample gates, truth contracts, reviewer-oriented repair loops, and long-running daemon controls. This paper describes the current XScientist architecture, the ARA protocol surface, and the practical safeguards needed to move autonomous science from single-run demos toward reproducible, reviewable, and forkable research infrastructure. The implementation and manuscript source are maintained in the public GitHub repository at https://github.com/smileformylove/XScientist.","short_abstract":"Autonomous research systems are often evaluated as one-shot paper generators: given a topic, they produce a manuscript and a small set of experiment logs. This framing hides the operational problem that makes such systems difficult to trust: research is long-running, branching, failure-prone, and dependent on auditable...","url_abs":"https://arxiv.org/abs/2607.12301","url_pdf":"https://arxiv.org/pdf/2607.12301v1","authors":"[\"Jixiang Luo\"]","published":"2026-07-14T03:20:11Z","proceeding":"cs.SE","tasks":"[\"cs.SE\",\"cs.MA\"]","methods":"[\"LoRA\"]","has_code":false,"code_links":[{"ID":614236,"CreatedAt":"2026-07-15T01:01:48.440468303Z","UpdatedAt":"2026-07-15T01:01:48.440468303Z","DeletedAt":null,"paper_id":6620460,"paper_url":"https://arxiv.org/abs/2607.12301","paper_title":"XScientist: A Git-Like Research Protocol for Long-Running Autonomous Scientific Discovery","repo_url":"https://github.com/smileformylove/XScientist","is_official":false,"mentioned_in_paper":false,"mentioned_in_github":true,"github_stars":0}]}