{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BAKUEWWFIEMDBCNVO2OMJDH6D7","short_pith_number":"pith:BAKUEWWF","schema_version":"1.0","canonical_sha256":"0815425ac541183089b5769cc48cfe1fd6626c88886d320ae909b4b272b76639","source":{"kind":"arxiv","id":"2506.09046","version":3},"attestation_state":"computed","paper":{"title":"Self-Evolving Multi-Agent Systems via Textual Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Chenyang Lin, Hinrich Schuetze, Jinhe Bi, Sikuan Yan, Volker Tresp, Xiaowen Ma, Yijun Tian, Yunpu Ma, Zixuan Cao","submitted_at":"2025-06-10T17:59:21Z","abstract_excerpt":"Leveraging multiple Large Language Models (LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network (ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative team focused on a specific subtask. Our framework follows a two-phase optimization strategy: (1) Forward Phase - Drawing inspiratio"},"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":"2506.09046","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-06-10T17:59:21Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"8a024247d937831ee8d24dc301373bc4938db48fb3622ec82da1af02261503dc","abstract_canon_sha256":"3398b0101b942d35407d2071dbc6fd42d492efea1cd215e032f5de2b13d573c4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:53.443035Z","signature_b64":"3YKiC0FyOShfnPWxIyKL3+pgT3uz3AMQFMICiFVB3TVDbcnYB/H9vxNPhvXaH+b2mP2pwdaHEqiSy2ZC4ZpsCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0815425ac541183089b5769cc48cfe1fd6626c88886d320ae909b4b272b76639","last_reissued_at":"2026-06-19T16:10:53.442587Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:53.442587Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Evolving Multi-Agent Systems via Textual Backpropagation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.LG","authors_text":"Chenyang Lin, Hinrich Schuetze, Jinhe Bi, Sikuan Yan, Volker Tresp, Xiaowen Ma, Yijun Tian, Yunpu Ma, Zixuan Cao","submitted_at":"2025-06-10T17:59:21Z","abstract_excerpt":"Leveraging multiple Large Language Models (LLMs) has proven effective for addressing complex, high-dimensional tasks, but current approaches often rely on static, manually engineered multi-agent configurations. To overcome these constraints, we present the Agentic Neural Network (ANN), a framework that conceptualizes multi-agent collaboration as a layered neural network architecture. In this design, each agent operates as a node, and each layer forms a cooperative team focused on a specific subtask. Our framework follows a two-phase optimization strategy: (1) Forward Phase - Drawing inspiratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.09046","kind":"arxiv","version":3},"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/2506.09046/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":"2506.09046","created_at":"2026-06-19T16:10:53.442643+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.09046v3","created_at":"2026-06-19T16:10:53.442643+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.09046","created_at":"2026-06-19T16:10:53.442643+00:00"},{"alias_kind":"pith_short_12","alias_value":"BAKUEWWFIEMD","created_at":"2026-06-19T16:10:53.442643+00:00"},{"alias_kind":"pith_short_16","alias_value":"BAKUEWWFIEMDBCNV","created_at":"2026-06-19T16:10:53.442643+00:00"},{"alias_kind":"pith_short_8","alias_value":"BAKUEWWF","created_at":"2026-06-19T16:10:53.442643+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2605.09341","citing_title":"SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2508.07407","citing_title":"A Comprehensive Survey of Self-Evolving AI Agents: A New Paradigm Bridging Foundation Models and Lifelong Agentic Systems","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09341","citing_title":"SkillMAS: Skill Co-Evolution with LLM-based Multi-Agent System","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7","json":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7.json","graph_json":"https://pith.science/api/pith-number/BAKUEWWFIEMDBCNVO2OMJDH6D7/graph.json","events_json":"https://pith.science/api/pith-number/BAKUEWWFIEMDBCNVO2OMJDH6D7/events.json","paper":"https://pith.science/paper/BAKUEWWF"},"agent_actions":{"view_html":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7","download_json":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7.json","view_paper":"https://pith.science/paper/BAKUEWWF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.09046&json=true","fetch_graph":"https://pith.science/api/pith-number/BAKUEWWFIEMDBCNVO2OMJDH6D7/graph.json","fetch_events":"https://pith.science/api/pith-number/BAKUEWWFIEMDBCNVO2OMJDH6D7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7/action/storage_attestation","attest_author":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7/action/author_attestation","sign_citation":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7/action/citation_signature","submit_replication":"https://pith.science/pith/BAKUEWWFIEMDBCNVO2OMJDH6D7/action/replication_record"}},"created_at":"2026-06-19T16:10:53.442643+00:00","updated_at":"2026-06-19T16:10:53.442643+00:00"}