{"paper":{"title":"Assistance to Autonomy: A Systematic Literature Review of Agentic AI across the Software Development Life Cycle","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Output verifiability enables agentic AI adoption mainly in later software development phases.","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Helena Holmstr\\\"om Olsson, Jan Bosch, Spyridon Alvanakis Apostolou","submitted_at":"2026-05-14T10:46:51Z","abstract_excerpt":"Agentic AI in software product development is increasingly adopted by organizations, yet the field lacks a consolidated synthesis of where adoption is mature, which architectural patterns dominate, and what limitations and coping mechanisms exist in industrial deployments. This systematic literature review addresses these gaps by establishing a body of knowledge as a starting point. Following Kitchenham guidelines, we queried four major research databases, obtaining over 1600 candidate publications. To handle this volume, we developed and validated a domain-agnostic multi-agent screening pipel"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"output verifiability is the primary enabler of agentic adoption: later SDLC phases, whose outputs are objectively evaluable through executable feedback, demonstrate the highest maturity and industrial presence, while earlier phases remain almost exclusively academic proofs-of-concept.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 92 manually verified primary studies, after multi-agent screening of over 1600 candidates, form a representative and unbiased sample whose thematic synthesis accurately reflects dominant patterns and industrial practices without significant omission of key work.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Systematic review of agentic AI in the SDLC finds output verifiability drives industrial adoption in later phases, with Planner-Executor-Reviewer as the dominant pattern, plus a new multi-agent LLM screening pipeline for high-volume SLRs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Output verifiability enables agentic AI adoption mainly in later software development phases.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"95251ed4f4f53348d1b1edadbcca50fa230739e19fa9af557539d32d6e49fc0f"},"source":{"id":"2605.15245","kind":"arxiv","version":1},"verdict":{"id":"58398205-9796-4f03-91b0-7730097dd60c","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T16:22:24.733504Z","strongest_claim":"output verifiability is the primary enabler of agentic adoption: later SDLC phases, whose outputs are objectively evaluable through executable feedback, demonstrate the highest maturity and industrial presence, while earlier phases remain almost exclusively academic proofs-of-concept.","one_line_summary":"Systematic review of agentic AI in the SDLC finds output verifiability drives industrial adoption in later phases, with Planner-Executor-Reviewer as the dominant pattern, plus a new multi-agent LLM screening pipeline for high-volume SLRs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 92 manually verified primary studies, after multi-agent screening of over 1600 candidates, form a representative and unbiased sample whose thematic synthesis accurately reflects dominant patterns and industrial practices without significant omission of key work.","pith_extraction_headline":"Output verifiability enables agentic AI adoption mainly in later software development phases."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15245/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_compliance","ran_at":"2026-05-19T16:36:28.763825Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:31:18.452911Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T15:41:54.409551Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.820741Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b49ed33e2a93b17566f403138598e910a5d743da5191375110bd4bd40ae39579"},"references":{"count":33,"sample":[{"doi":"","year":2025,"title":"IEEE Access13, 18912–18936 (2025), https://ieeexplore.ieee.org/abstract/document/10849561","work_id":"ad2afa48-4985-4442-be00-4d29005e859e","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"In: 2025 IEEE International Conference for Women in Innovation, Technology & Entrepreneurship (ICWITE)","work_id":"da4ea02a-d356-4fda-8fbf-a37e2afd51e6","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Akbar, M.A., Khan, A.A., Hamza, M., et al.: Agentic AI in Software Engineering: Practitioner Perspectives Across the Software Development Life Cycle (Sep 2025), https://papers.ssrn.com/abstract=552015","work_id":"06f3a2ea-0884-4ed9-9c89-ff36cf630d34","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Future Internet17(9) (Sep 2025),https://www.mdpi.com/1999-5903/ 17/9/404","work_id":"adae54de-796d-4f56-880b-15d170b6f1d3","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Measuring the impact of early-2025 AI on experienced open-source developer productivity.CoRR, abs/2507.09089","work_id":"5cc62c11-dd1e-43cc-83ff-88186859b97d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":33,"snapshot_sha256":"799c0d87ee5ff3ab021e1aa79329f3b5430fe255f9b90c692446b92d28b08fbe","internal_anchors":2},"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"}