{"paper":{"title":"RAT: RunAnyThing via Fully Automated Environment Configuration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"RAT enables fully automated environment configuration for arbitrary software repositories using a language-agnostic multi-stage pipeline.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Daixin Wang, Dongdong Hua, Hanyang Yuan, Renhong Huang, Sitao Ding, Yang Yang, Yifei Sun","submitted_at":"2026-04-25T07:45:41Z","abstract_excerpt":"Automating repository-level software engineering tasks is a foundational challenge for autonomous code agents, largely due to the difficulty of configuring executable environments. However, manual configuration remains a labor-intensive bottleneck, necessitating a transition toward fully automated environment configuration. Existing approaches often rely on pre-defined artifacts or are restricted to specific programming languages, limiting their applicability to diverse real-world repositories. In this paper, we first propose RAT (RunAnyThing), a modular and extensible agent framework for full"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RAT achieves state-of-the-art performance, improving the Environment Setup Success Rate (ESSR) by an average of 29.6% over strong baselines.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the multi-stage pipeline integrating semantic initialization, planning, specialized toolset, and sandbox can reliably handle the distribution and heterogeneity of arbitrary real-world repositories without manual intervention or language-specific restrictions.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RAT is a new language-agnostic system that automates environment configuration for any code repository and improves setup success rate by 29.6% over baselines on the new RATBench benchmark.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RAT enables fully automated environment configuration for arbitrary software repositories using a language-agnostic multi-stage pipeline.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c82df24c7672a8f0f62bec911d22e4f58defd3da989c257778be19507e50a4ca"},"source":{"id":"2604.23190","kind":"arxiv","version":2},"verdict":{"id":"16bd986f-bb58-4b78-8bfe-6f8beb48a7f1","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-08T08:01:41.896810Z","strongest_claim":"RAT achieves state-of-the-art performance, improving the Environment Setup Success Rate (ESSR) by an average of 29.6% over strong baselines.","one_line_summary":"RAT is a new language-agnostic system that automates environment configuration for any code repository and improves setup success rate by 29.6% over baselines on the new RATBench benchmark.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the multi-stage pipeline integrating semantic initialization, planning, specialized toolset, and sandbox can reliably handle the distribution and heterogeneity of arbitrary real-world repositories without manual intervention or language-specific restrictions.","pith_extraction_headline":"RAT enables fully automated environment configuration for arbitrary software repositories using a language-agnostic multi-stage pipeline."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.23190/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-21T09:37:49.355972Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T23:24:09.816998Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"cd6fe6142f7b6b79d73e544c7d66d6c4f043b31e0c0e09a0a5aafdf1e77b96a8"},"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"}