{"paper":{"title":"CLI-Anything: Towards Agent-Native Computer Use","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Chao Huang, Tianyu Fan, Yuhao Yang","submitted_at":"2026-06-02T16:30:33Z","abstract_excerpt":"As large language models advance in reasoning and tool use capabilities, researchers increasingly seek to leverage them for computer use agents that can interact with existing software. The dominant approach develops GUI agents that control applications through visual interfaces: interpreting screenshots, locating UI elements, and executing mouse clicks to mimic human interaction. This GUI-centric paradigm fundamentally misaligns with agent capabilities. Current GUI agents struggle with brittle pixel-level interactions, timing dependencies, and coordinate-based actions that break with interfac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.03854","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2606.03854/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}