{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T3CR6JFHOFOPJ2VZFHDG6BZBF4","short_pith_number":"pith:T3CR6JFH","schema_version":"1.0","canonical_sha256":"9ec51f24a7715cf4eab929c66f07212f2b506487ca4ee094e50bfb84816c50f5","source":{"kind":"arxiv","id":"2508.00083","version":2},"attestation_state":"computed","paper":{"title":"A Survey on Code Generation with LLM-based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Ge Li, Jiaru Qian, Kechi Zhang, Tian Wang, Xue Jiang, Yihong Dong, Zhi Jin","submitted_at":"2025-07-31T18:17:36Z","abstract_excerpt":"Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm. Distinct from previous code generation techniques, code generation agents are characterized by three core features. 1) Autonomy: the ability to independently manage the entire workflow, from task decomposition to coding and debugging. 2) Expanded task scope: capabilities that extend beyond generating code snippets to encompass the full software development lifecycle (SDLC). 3) Enhancement of engineering practicality: a shift in research emphasis from algorithmic innovation towa"},"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":"2508.00083","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2025-07-31T18:17:36Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"5b97eb192ecf59bf21affd35cbc7c3e93573c142040722ca97bfce57e8db15b8","abstract_canon_sha256":"c6a5b9ad22873567c0e5e40cdc4e73b6f0789299e2983674517e85bd4743bb88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-19T22:57:49.313733Z","signature_b64":"XeJwX6ELVTpAi8vAIQWtJkdnjJCheQh92yo0fqNgYlUKk+93Ch2CpxV79nUOvbp5sHovYpprXDYfbfpib+hqAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ec51f24a7715cf4eab929c66f07212f2b506487ca4ee094e50bfb84816c50f5","last_reissued_at":"2026-05-19T22:57:49.312003Z","signature_status":"signed_v1","first_computed_at":"2026-05-19T22:57:49.312003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Code Generation with LLM-based Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.SE","authors_text":"Ge Li, Jiaru Qian, Kechi Zhang, Tian Wang, Xue Jiang, Yihong Dong, Zhi Jin","submitted_at":"2025-07-31T18:17:36Z","abstract_excerpt":"Code generation agents powered by large language models (LLMs) are revolutionizing the software development paradigm. Distinct from previous code generation techniques, code generation agents are characterized by three core features. 1) Autonomy: the ability to independently manage the entire workflow, from task decomposition to coding and debugging. 2) Expanded task scope: capabilities that extend beyond generating code snippets to encompass the full software development lifecycle (SDLC). 3) Enhancement of engineering practicality: a shift in research emphasis from algorithmic innovation towa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00083","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/2508.00083/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":"2508.00083","created_at":"2026-05-19T22:57:49.312082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00083v2","created_at":"2026-05-19T22:57:49.312082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00083","created_at":"2026-05-19T22:57:49.312082+00:00"},{"alias_kind":"pith_short_12","alias_value":"T3CR6JFHOFOP","created_at":"2026-05-19T22:57:49.312082+00:00"},{"alias_kind":"pith_short_16","alias_value":"T3CR6JFHOFOPJ2VZ","created_at":"2026-05-19T22:57:49.312082+00:00"},{"alias_kind":"pith_short_8","alias_value":"T3CR6JFH","created_at":"2026-05-19T22:57:49.312082+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":31,"internal_anchor_count":31,"sample":[{"citing_arxiv_id":"2512.04111","citing_title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2601.11650","citing_title":"Large Language Model Agent for User-friendly Chemical Process Simulations","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2512.04111","citing_title":"CentaurEval: Benchmarking Human-in-the-Loop Value in Agentic Coding","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20456","citing_title":"Agentic Agile-V: From Vibe Coding to Verified Engineering in Software and Hardware Development","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.21133","citing_title":"Humanoid Whole-Body Manipulation via Active Spatial Brain and Generalizable Action Cerebellum","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":177,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19382","citing_title":"PRISM: A Benchmark for Programmatic Spatial-Temporal Reasoning","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17242","citing_title":"From Runnable to Shippable: Multi-Agent Test-Driven Development for Generating Full-Stack Web Applications from Requirements","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17526","citing_title":"SaaSBench: Exploring the Boundaries of Coding Agents in Long-Horizon Enterprise SaaS Engineering","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15766","citing_title":"BioXArena: Benchmarking LLM Agents on Multi-Modal Biomedical Machine Learning Tasks","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15222","citing_title":"PerfCodeBench: Benchmarking LLMs for System-Level High-Performance Code Optimization","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2510.18471","citing_title":"CodeRL+: Improving Code Generation via Reinforcement with Execution Semantics Alignment","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.16314","citing_title":"Software Self-Extension with SelfEvolve: an Agentic Architecture for Runtime Code Generation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09564","citing_title":"ACE-Bench: A Lightweight Benchmark for Evaluating Azure SDK Usage Correctness","ref_index":3,"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":86,"is_internal_anchor":true},{"citing_arxiv_id":"2603.00989","citing_title":"Sustainable Code Generation Using Large Language Models: A Systematic Literature Review","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13050","citing_title":"Context Training with Active Information Seeking","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13050","citing_title":"Context Training with Active Information Seeking","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29957","citing_title":"Think Anywhere in Code Generation","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02776","citing_title":"Evaluating the Environmental Impact of using SLMs and Prompt Engineering for Code Generation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02709","citing_title":"Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.11665","citing_title":"Nautilus: From One Prompt to Plug-and-Play Robot Learning","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26615","citing_title":"TDD Governance for Multi-Agent Code Generation via Prompt Engineering","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4","json":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4.json","graph_json":"https://pith.science/api/pith-number/T3CR6JFHOFOPJ2VZFHDG6BZBF4/graph.json","events_json":"https://pith.science/api/pith-number/T3CR6JFHOFOPJ2VZFHDG6BZBF4/events.json","paper":"https://pith.science/paper/T3CR6JFH"},"agent_actions":{"view_html":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4","download_json":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4.json","view_paper":"https://pith.science/paper/T3CR6JFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00083&json=true","fetch_graph":"https://pith.science/api/pith-number/T3CR6JFHOFOPJ2VZFHDG6BZBF4/graph.json","fetch_events":"https://pith.science/api/pith-number/T3CR6JFHOFOPJ2VZFHDG6BZBF4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4/action/storage_attestation","attest_author":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4/action/author_attestation","sign_citation":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4/action/citation_signature","submit_replication":"https://pith.science/pith/T3CR6JFHOFOPJ2VZFHDG6BZBF4/action/replication_record"}},"created_at":"2026-05-19T22:57:49.312082+00:00","updated_at":"2026-05-19T22:57:49.312082+00:00"}