{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:4TP7XO6ORR3PDA3HRO3U2BI7PR","short_pith_number":"pith:4TP7XO6O","schema_version":"1.0","canonical_sha256":"e4dffbbbce8c76f183678bb74d051f7c5689f8d326af3b18a4cec278c0feed87","source":{"kind":"arxiv","id":"2411.12924","version":2},"attestation_state":"computed","paper":{"title":"Human-In-the-Loop Software Development Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chakkrit Tantithamthavorn, Evan Cook, Fan Jiang, Jing Li, Jirat Pasuksmit, Kun Chen, Ming Wu, Patanamon Thongtanunam, Ruixiong Zhang, Wannita Takerngsaksiri","submitted_at":"2024-11-19T23:22:33Z","abstract_excerpt":"Recently, Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks (e.g., from a given issue to source code). However, existing work is evaluated based on historical benchmark datasets, rarely considers human feedback at each stage of the automated software development process, and has not been deployed in practice. In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plan"},"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":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2411.12924","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SE","submitted_at":"2024-11-19T23:22:33Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"761d4724844e9cc08ffa3d7ee6fa7a24fc08948388d60a80709b4adee2b72399","abstract_canon_sha256":"109031b0a1f3cd55c939ba87c9915d55abb2440b9b11c1a952b8cdeb0f779303"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:20.532076Z","signature_b64":"bAVAeEV5HCKpVuSztdgC7Cuz7WWwZDte3bpCn4STIY9niDohj1JaA4nSAkgqaC8QauWpN1mQeJL+Gn8fIEYXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4dffbbbce8c76f183678bb74d051f7c5689f8d326af3b18a4cec278c0feed87","last_reissued_at":"2026-07-05T09:59:20.531567Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:20.531567Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Human-In-the-Loop Software Development Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.SE","authors_text":"Chakkrit Tantithamthavorn, Evan Cook, Fan Jiang, Jing Li, Jirat Pasuksmit, Kun Chen, Ming Wu, Patanamon Thongtanunam, Ruixiong Zhang, Wannita Takerngsaksiri","submitted_at":"2024-11-19T23:22:33Z","abstract_excerpt":"Recently, Large Language Models (LLMs)-based multi-agent paradigms for software engineering are introduced to automatically resolve software development tasks (e.g., from a given issue to source code). However, existing work is evaluated based on historical benchmark datasets, rarely considers human feedback at each stage of the automated software development process, and has not been deployed in practice. In this paper, we introduce a Human-in-the-loop LLM-based Agents framework (HULA) for software development that allows software engineers to refine and guide LLMs when generating coding plan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12924","kind":"arxiv","version":2},"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/2411.12924/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2411.12924","created_at":"2026-07-05T09:59:20.531638+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.12924v2","created_at":"2026-07-05T09:59:20.531638+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12924","created_at":"2026-07-05T09:59:20.531638+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TP7XO6ORR3P","created_at":"2026-07-05T09:59:20.531638+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TP7XO6ORR3PDA3H","created_at":"2026-07-05T09:59:20.531638+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TP7XO6O","created_at":"2026-07-05T09:59:20.531638+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22484","citing_title":"Governed AI-Assisted Engineering: Graduated Human Oversight for Agentic Code Generation in Regulated Domains","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.24598","citing_title":"Toward Self-Evolution-Ready Workflow Harnesses: A Reversible Migration Path and Convertibility Taxonomy for Expert LLM Pipelines","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2508.15503","citing_title":"Guidelines for Empirical Studies in Software Engineering involving Large Language Models","ref_index":131,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09564","citing_title":"ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":83,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR","json":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR.json","graph_json":"https://pith.science/api/pith-number/4TP7XO6ORR3PDA3HRO3U2BI7PR/graph.json","events_json":"https://pith.science/api/pith-number/4TP7XO6ORR3PDA3HRO3U2BI7PR/events.json","paper":"https://pith.science/paper/4TP7XO6O"},"agent_actions":{"view_html":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR","download_json":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR.json","view_paper":"https://pith.science/paper/4TP7XO6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.12924&json=true","fetch_graph":"https://pith.science/api/pith-number/4TP7XO6ORR3PDA3HRO3U2BI7PR/graph.json","fetch_events":"https://pith.science/api/pith-number/4TP7XO6ORR3PDA3HRO3U2BI7PR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR/action/storage_attestation","attest_author":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR/action/author_attestation","sign_citation":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR/action/citation_signature","submit_replication":"https://pith.science/pith/4TP7XO6ORR3PDA3HRO3U2BI7PR/action/replication_record"}},"created_at":"2026-07-05T09:59:20.531638+00:00","updated_at":"2026-07-05T09:59:20.531638+00:00"}