{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SCZRVMD4JQDM6PRZH2FIUETIUJ","short_pith_number":"pith:SCZRVMD4","schema_version":"1.0","canonical_sha256":"90b31ab07c4c06cf3e393e8a8a1268a2671dcbf5504204b95d4cdc95a8b5bd39","source":{"kind":"arxiv","id":"2608.04872","version":1},"attestation_state":"computed","paper":{"title":"A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dong Liu, Fei Ben, Fenghua Ling, Feng Liu, Haobo Li, Kaiyi Xu, Lei Bai, Shu Wang, Wenhao Li, Wenxiao Zhao, Yingnian Wu, Zhen Zhao","submitted_at":"2026-08-05T14:01:10Z","abstract_excerpt":"Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt. We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views. A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory. During search, evaluator feedback characterizes reliability and productivity, upd"},"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":"2608.04872","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-08-05T14:01:10Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"80cd1a80931ee913940680980202ee4c116cf2076724012393e58a6d4c83d6e7","abstract_canon_sha256":"f82b9f61a4e9d843bca5721552ad2cb3e59789f7c2d6d604b169cb96a625a653"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:47:26.346067Z","signature_b64":"eJyPn9khehPjYBhcIdXMm3uuNnSDcR8u/DYL4CNqlKG3Jymwe6gzXUVBrZsOW13lP7AkqbTjckNK6iyPGUslBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"90b31ab07c4c06cf3e393e8a8a1268a2671dcbf5504204b95d4cdc95a8b5bd39","last_reissued_at":"2026-08-06T01:47:26.344603Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:47:26.344603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A-SR: Self-Evolving Agentic LLMs for Symbolic Regression via Hierarchical Coordination","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dong Liu, Fei Ben, Fenghua Ling, Feng Liu, Haobo Li, Kaiyi Xu, Lei Bai, Shu Wang, Wenhao Li, Wenxiao Zhao, Yingnian Wu, Zhen Zhao","submitted_at":"2026-08-05T14:01:10Z","abstract_excerpt":"Symbolic regression aims to discover closed-form equations from data, but existing LLM-guided methods often rely on a unified proposal loop that compresses heterogeneous search failures into a scalar score and a single prompt. We propose A-SR, a self-evolving agentic framework that shifts the control unit from expression edits to role-conditioned evidence views. A-SR coordinates formula discovery through routing among coordination protocols, an online evaluator-reward role policy, and state-routed process memory. During search, evaluator feedback characterizes reliability and productivity, upd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04872","kind":"arxiv","version":1},"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/2608.04872/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":"2608.04872","created_at":"2026-08-06T01:47:26.346457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04872v1","created_at":"2026-08-06T01:47:26.346457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04872","created_at":"2026-08-06T01:47:26.346457+00:00"},{"alias_kind":"pith_short_12","alias_value":"SCZRVMD4JQDM","created_at":"2026-08-06T01:47:26.346457+00:00"},{"alias_kind":"pith_short_16","alias_value":"SCZRVMD4JQDM6PRZ","created_at":"2026-08-06T01:47:26.346457+00:00"},{"alias_kind":"pith_short_8","alias_value":"SCZRVMD4","created_at":"2026-08-06T01:47:26.346457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.09568","citing_title":"Se-DPO: Self-Evolving Token Credit for Direct Preference Optimization","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ","json":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ.json","graph_json":"https://pith.science/api/pith-number/SCZRVMD4JQDM6PRZH2FIUETIUJ/graph.json","events_json":"https://pith.science/api/pith-number/SCZRVMD4JQDM6PRZH2FIUETIUJ/events.json","paper":"https://pith.science/paper/SCZRVMD4"},"agent_actions":{"view_html":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ","download_json":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ.json","view_paper":"https://pith.science/paper/SCZRVMD4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04872&json=true","fetch_graph":"https://pith.science/api/pith-number/SCZRVMD4JQDM6PRZH2FIUETIUJ/graph.json","fetch_events":"https://pith.science/api/pith-number/SCZRVMD4JQDM6PRZH2FIUETIUJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ/action/storage_attestation","attest_author":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ/action/author_attestation","sign_citation":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ/action/citation_signature","submit_replication":"https://pith.science/pith/SCZRVMD4JQDM6PRZH2FIUETIUJ/action/replication_record"}},"created_at":"2026-08-06T01:47:26.346457+00:00","updated_at":"2026-08-06T01:47:26.346457+00:00"}