{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ONRDOB345KFXIPZDCKNAK3YQJK","short_pith_number":"pith:ONRDOB34","schema_version":"1.0","canonical_sha256":"736237077cea8b743f23129a056f104a9f2e003b65d320fa47932fcb3a40c620","source":{"kind":"arxiv","id":"2409.02977","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2409.02977","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-09-04T15:59:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"810cc8f9984bd735b2c41c993d66cced9a41c4e023da8047ac40bb7015218286","abstract_canon_sha256":"5587aa4f1c01310a73ea5f4115aa53ba7ae2409d631937337c93ca25217bf94a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.097799Z","signature_b64":"4d1J3OSDNB4naHqKe4UiRxfBvPBAVA4KAKFDakXUNfioNtZkuAL6mVa+8FRDE/YCD6Jk8neaj+1DPQaKXnBGDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"736237077cea8b743f23129a056f104a9f2e003b65d320fa47932fcb3a40c620","last_reissued_at":"2026-05-17T23:38:14.096973Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.096973Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2409.02977","created_at":"2026-05-17T23:38:14.097103+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.02977v2","created_at":"2026-05-17T23:38:14.097103+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02977","created_at":"2026-05-17T23:38:14.097103+00:00"},{"alias_kind":"pith_short_12","alias_value":"ONRDOB345KFX","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"ONRDOB345KFXIPZD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"ONRDOB34","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":19,"sample":[{"citing_arxiv_id":"2510.01453","citing_title":"The Command Line GUIde: Graphical Interfaces from Man Pages via AI","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2510.06452","citing_title":"Code Semantic Zooming","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2511.02399","citing_title":"EvoDev: An Iterative Feature-Driven Framework for End-to-End Software Development with LLM-based Agents","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16321","citing_title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16335","citing_title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2603.26567","citing_title":"Beyond Code Snippets: Benchmarking LLMs on Repository-Level Question Answering","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12913","citing_title":"Revisiting DAgger in the Era of LLM-Agents","ref_index":21,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02547","citing_title":"Beyond Resolution Rates: Behavioral Drivers of Coding Agent Success and Failure","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2407.01489","citing_title":"Agentless: Demystifying LLM-based Software Engineering Agents","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24212","citing_title":"Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12301","citing_title":"Local-Splitter: A Measurement Study of Seven Tactics for Reducing Cloud LLM Token Usage on Coding-Agent Workloads","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07341","citing_title":"ReCodeAgent: A Multi-Agent Workflow for Language-agnostic Translation and Validation of Large-scale Repositories","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07769","citing_title":"An Empirical Study on Influence-Based Pretraining Data Selection for Code Large Language Models","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07062","citing_title":"From Assistance to Agency: Rethinking Autonomy and Control in CI/CD Pipelines","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06742","citing_title":"Evaluating LLM-Based 0-to-1 Software Generation in End-to-End CLI Tool Scenarios","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05753","citing_title":"An End-to-End Approach for Fixing Concurrency Bugs via SHB-Based Context Extractor","ref_index":109,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05289","citing_title":"FLARE: Agentic Coverage-Guided Fuzzing for LLM-Based Multi-Agent Systems","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15468","citing_title":"The Semi-Executable Stack: Agentic Software Engineering and the Expanding Scope of SE","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16790","citing_title":"Bias in the Loop: Auditing LLM-as-a-Judge for Software Engineering","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK","json":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK.json","graph_json":"https://pith.science/api/pith-number/ONRDOB345KFXIPZDCKNAK3YQJK/graph.json","events_json":"https://pith.science/api/pith-number/ONRDOB345KFXIPZDCKNAK3YQJK/events.json","paper":"https://pith.science/paper/ONRDOB34"},"agent_actions":{"view_html":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK","download_json":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK.json","view_paper":"https://pith.science/paper/ONRDOB34","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.02977&json=true","fetch_graph":"https://pith.science/api/pith-number/ONRDOB345KFXIPZDCKNAK3YQJK/graph.json","fetch_events":"https://pith.science/api/pith-number/ONRDOB345KFXIPZDCKNAK3YQJK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK/action/storage_attestation","attest_author":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK/action/author_attestation","sign_citation":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK/action/citation_signature","submit_replication":"https://pith.science/pith/ONRDOB345KFXIPZDCKNAK3YQJK/action/replication_record"}},"created_at":"2026-05-17T23:38:14.097103+00:00","updated_at":"2026-05-17T23:38:14.097103+00:00"}