{"paper":{"title":"Large Language Model-Based Agents for Software Engineering: A Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"This survey gathers 124 papers on LLM-based agents for software engineering and sorts them by software engineering tasks and agent structures.","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Junwei Liu, Kaixin Wang, Lingming Zhang, Xin Peng, Yiling Lou, Yixuan Chen, Zhenpeng Chen","submitted_at":"2024-09-04T15:59:41Z","abstract_excerpt":"The recent advance in Large Language Models (LLMs) has shaped a new paradigm of AI agents, i.e., LLM-based agents. Compared to standalone LLMs, LLM-based agents substantially extend the versatility and expertise of LLMs by enhancing LLMs with the capabilities of perceiving and utilizing external resources and tools. To date, LLM-based agents have been applied and shown remarkable effectiveness in Software Engineering (SE). The synergy between multiple agents and human interaction brings further promise in tackling complex real-world SE problems. In this work, we present a comprehensive and sys"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 124 papers and categorize them from two perspectives, i.e., the SE and agent perspectives.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the 124 collected papers form a representative sample of the field and that the chosen two-perspective categorization sufficiently captures the essential distinctions without significant omissions or overlaps.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"This survey gathers 124 papers on LLM-based agents for software engineering and sorts them by software engineering tasks and agent structures.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"53b3f8c5623cfae7b6476b2b92b5d18189f3939779fd8dfca349682d05e7c3cf"},"source":{"id":"2409.02977","kind":"arxiv","version":2},"verdict":{"id":"79d7de66-cada-4743-8a8e-010bef72ded0","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T12:29:16.894990Z","strongest_claim":"In this work, we present a comprehensive and systematic survey on LLM-based agents for SE. We collect 124 papers and categorize them from two perspectives, i.e., the SE and agent perspectives.","one_line_summary":"A literature survey that collects and categorizes 124 papers on LLM-based agents for software engineering from SE and agent perspectives.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the 124 collected papers form a representative sample of the field and that the chosen two-perspective categorization sufficiently captures the essential distinctions without significant omissions or overlaps.","pith_extraction_headline":"This survey gathers 124 papers on LLM-based agents for software engineering and sorts them by software engineering tasks and agent structures."},"references":{"count":290,"sample":[{"doi":"","year":2023,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","ref_index":1,"cited_arxiv_id":"2303.18223","is_internal_anchor":true},{"doi":"","year":2024,"title":"Large language models for software engineering: A systematic literature review.ACM Trans","work_id":"fb5a7f01-49be-49cd-8c74-aed637f9fd21","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Angela Fan, Beliz Gokkaya, Mark Harman, Mitya Lyubarskiy, Shubho Sengupta, Shin Yoo, and Jie M. Zhang. Large language models for software engineering: Survey and open problems. In IEEE/ACM Internation","work_id":"6885f599-0a75-4049-8519-2a71e1a0cb62","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Self-collaboration code generation via chatgpt.ACM Trans","work_id":"0a065ebc-e2ce-4a79-b357-213ab84e149d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Evaluating the code quality of AI-assisted code generation tools: An empirical study on GitHub Copilot, Amazon Code- Whisperer, and ChatGPT","work_id":"fc34d942-a4d6-4670-b39a-c6c5537410cb","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":290,"snapshot_sha256":"d4a5dc8db59d6151a753622e7347dbbced6388b63627dfe8c9fecc24a8c34274","internal_anchors":13},"formal_canon":{"evidence_count":2,"snapshot_sha256":"66813ca420250f7051eec0b020f42d8005effaf39afdcd91828fa364dd848f2a"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}