{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/towards-agentic-schema-refinement","title":"Towards Agentic Schema Refinement","arxiv_id":"2412.07786","date":"2024-11-25","proceeding":null,"authors":["Agapi Rissaki","Ilias Fountalis","Nikolaos Vasiloglou","Wolfgang Gatterbauer"],"abstract":"Large enterprise databases can be complex and messy, obscuring the data semantics needed for analytical tasks. We propose a semantic layer in-between the database and the user as a set of small and easy-to-interpret database views, effectively acting as a refined version of the schema. To discover these views, we introduce a multi-agent Large Language Model (LLM) simulation where LLM agents collaborate to iteratively define and refine views with minimal input. Our approach paves the way for LLM-powered exploration of unwieldy databases.","url_abs":"https://arxiv.org/abs/2412.07786v1","url_pdf":"https://arxiv.org/pdf/2412.07786v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"language-modeling","task_name":"Language Modeling"},{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"large-language-model","task_name":"Large Language Model"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2412.07786","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2412.07786"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"deterministic:regex_extraction","url":"https://github.com/agapiR/agentic-semantic-layer","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":1,"unverified":13},"by_repo_kind":{"found_in_text":{"samples":14,"ran":1,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"c4dcaf29b663a364","entry":"get_schema_from_json","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/process_sql.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/process_sql.py","link_basis":"plan_row","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"c4dcaf29b663a364"}},{"code_sha256_prefix":"83f8464f9322b98b","entry":"extract_json_from_llm_response","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/utils.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"83f8464f9322b98b"}},{"code_sha256_prefix":"086c2f0c0702ca1c","entry":"extract_view_definitions_from_code","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/refinement.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/refinement.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"086c2f0c0702ca1c"}},{"code_sha256_prefix":"1108e7e4dbfda5f1","entry":"get_sql_from_text","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/postprocess.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/postprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"1108e7e4dbfda5f1"}},{"code_sha256_prefix":"7db43e037cfb3234","entry":"get_view_name_from_definition","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/database_utils.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/database_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7db43e037cfb3234"}},{"code_sha256_prefix":"ec715f53ac4ec296","entry":"parse_chats_from_log","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/postprocess.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/postprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ec715f53ac4ec296"}},{"code_sha256_prefix":"7aa1b727147007ab","entry":"parse_chats_from_log_without_schema","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/postprocess.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/postprocess.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7aa1b727147007ab"}},{"code_sha256_prefix":"2c2314d7ff144be3","entry":"prompt_llm","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/utils.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2c2314d7ff144be3"}},{"code_sha256_prefix":"3031ce44bc594f0c","entry":"sample_connected_subgraph_nodes","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/graph.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/graph.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3031ce44bc594f0c"}},{"code_sha256_prefix":"82406997bc71a7b5","entry":"scan_alias","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/process_sql.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/process_sql.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"82406997bc71a7b5"}},{"code_sha256_prefix":"b411f1ad74a8198a","entry":"schema_graph","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/graph.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/graph.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"b411f1ad74a8198a"}},{"code_sha256_prefix":"8d3026c3243f3635","entry":"schema_subgraph","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/graph.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/graph.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"8d3026c3243f3635"}},{"code_sha256_prefix":"0976456abb329f60","entry":"text_embedding","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/utils.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"0976456abb329f60"}},{"code_sha256_prefix":"a906f5de1f5971b0","entry":"tokenize","repo":"agapiR/agentic-semantic-layer","repo_kind":"found_in_text","path":"src/process_sql.py","file_url":"https://github.com/agapiR/agentic-semantic-layer/blob/HEAD/src/process_sql.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"a906f5de1f5971b0"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}