{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UL3V7M5GIKWX5AFTTMPWGODW2Y","short_pith_number":"pith:UL3V7M5G","schema_version":"1.0","canonical_sha256":"a2f75fb3a642ad7e80b39b1f633876d6030de4648f8b2d72dc30966e81f6ae8b","source":{"kind":"arxiv","id":"2403.17134","version":2},"attestation_state":"computed","paper":{"title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Islem Bouzenia, Michael Pradel, Premkumar Devanbu","submitted_at":"2024-03-25T19:17:43Z","abstract_excerpt":"Automated program repair has emerged as a powerful technique to mitigate the impact of software bugs on system reliability and user experience. This paper introduces RepairAgent, the first work to address the program repair challenge through an autonomous agent based on a large language model (LLM). Unlike existing deep learning-based approaches, which prompt a model with a fixed prompt or in a fixed feedback loop, our work treats the LLM as an agent capable of autonomously planning and executing actions to fix bugs by invoking suitable tools. RepairAgent freely interleaves gathering informati"},"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":"2403.17134","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2024-03-25T19:17:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"440adca69bcbdeb59d3a9a81215f8f00a04bb3bd1ac2479f609fad010ea0266d","abstract_canon_sha256":"db8b344b9ea631a999d4e426e82617d05706a24ee3c5aa02850a9384fd839308"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T10:15:51.468999Z","signature_b64":"FO4/5wpbmtzHi2t6r4XqfsKmmIjLxyrDgEjRlIzvo/XQCdSxX0trbSBGGzhAbK7ooNP7f2OJL3UoBWwqdYubCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f75fb3a642ad7e80b39b1f633876d6030de4648f8b2d72dc30966e81f6ae8b","last_reissued_at":"2026-05-19T10:15:51.466681Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T10:15:51.466681Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SE","authors_text":"Islem Bouzenia, Michael Pradel, Premkumar Devanbu","submitted_at":"2024-03-25T19:17:43Z","abstract_excerpt":"Automated program repair has emerged as a powerful technique to mitigate the impact of software bugs on system reliability and user experience. This paper introduces RepairAgent, the first work to address the program repair challenge through an autonomous agent based on a large language model (LLM). Unlike existing deep learning-based approaches, which prompt a model with a fixed prompt or in a fixed feedback loop, our work treats the LLM as an agent capable of autonomously planning and executing actions to fix bugs by invoking suitable tools. RepairAgent freely interleaves gathering informati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.17134","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/2403.17134/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":"2403.17134","created_at":"2026-05-19T10:15:51.466779+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.17134v2","created_at":"2026-05-19T10:15:51.466779+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.17134","created_at":"2026-05-19T10:15:51.466779+00:00"},{"alias_kind":"pith_short_12","alias_value":"UL3V7M5GIKWX","created_at":"2026-05-19T10:15:51.466779+00:00"},{"alias_kind":"pith_short_16","alias_value":"UL3V7M5GIKWX5AFT","created_at":"2026-05-19T10:15:51.466779+00:00"},{"alias_kind":"pith_short_8","alias_value":"UL3V7M5G","created_at":"2026-05-19T10:15:51.466779+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.17965","citing_title":"BLAgent: Agentic RAG for File-Level Bug Localization","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17444","citing_title":"MemRepair: Hierarchical Memory for Agentic Repository-Level Vulnerability Repair","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2506.01770","citing_title":"ReGA: Model-Based Safeguard for LLMs via Representation-Guided Abstraction","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2506.10484","citing_title":"EXPEREPAIR: Dual-Memory Enhanced LLM-based Repository-Level Program Repair","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2508.12232","citing_title":"LinkAnchor: An Autonomous LLM-Based Agent for Issue-to-Commit Link Recovery","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2508.16419","citing_title":"Can LLMs Find Bugs in Code? An Evaluation from Beginner Errors to Security Vulnerabilities in Python and C++","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2510.15494","citing_title":"Do AI Models Dream of Faster Code? An Empirical Study on LLM-Proposed Performance Improvements in Real-World Software","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2511.00780","citing_title":"Can Language Models Go Beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2602.02280","citing_title":"RACC: Representation-Aware Coverage Criteria for LLM Safety Testing","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2502.18449","citing_title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","ref_index":116,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08717","citing_title":"Debugging the Debuggers: Failure-Anchored Structured Recovery for Software Engineering Agents","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2407.01489","citing_title":"Agentless: Demystifying LLM-based Software Engineering Agents","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08621","citing_title":"EvidenT: An Evidence-Preserving Framework for Iterative System-Level Package Repair","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25399","citing_title":"CoRE: A Fine-Grained Code Reasoning Benchmark Beyond Output Prediction","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24212","citing_title":"Empowering Autonomous Debugging Agents with Efficient Dynamic Analysis","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2604.19305","citing_title":"DebugRepair: Enhancing LLM-Based Automated Program Repair via Self-Directed Debugging","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12108","citing_title":"LLM-Based Automated Diagnosis Of Integration Test Failures At Google","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07624","citing_title":"Program Analysis Guided LLM Agent for Proof-of-Concept Generation","ref_index":7,"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":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02215","citing_title":"HEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2604.04580","citing_title":"Beyond Fixed Tests: Repository-Level Issue Resolution as Coevolution of Code and Behavioral Constraints","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17016","citing_title":"HELO-APR: Enhancing Low-Resource Program Repair through Cross-Lingual Knowledge Transfer","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02215","citing_title":"HEJ-Robust: A Robustness Benchmark for LLM-Based Automated Program Repair","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y","json":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y.json","graph_json":"https://pith.science/api/pith-number/UL3V7M5GIKWX5AFTTMPWGODW2Y/graph.json","events_json":"https://pith.science/api/pith-number/UL3V7M5GIKWX5AFTTMPWGODW2Y/events.json","paper":"https://pith.science/paper/UL3V7M5G"},"agent_actions":{"view_html":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y","download_json":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y.json","view_paper":"https://pith.science/paper/UL3V7M5G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.17134&json=true","fetch_graph":"https://pith.science/api/pith-number/UL3V7M5GIKWX5AFTTMPWGODW2Y/graph.json","fetch_events":"https://pith.science/api/pith-number/UL3V7M5GIKWX5AFTTMPWGODW2Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y/action/storage_attestation","attest_author":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y/action/author_attestation","sign_citation":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y/action/citation_signature","submit_replication":"https://pith.science/pith/UL3V7M5GIKWX5AFTTMPWGODW2Y/action/replication_record"}},"created_at":"2026-05-19T10:15:51.466779+00:00","updated_at":"2026-05-19T10:15:51.466779+00:00"}