{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VTJNFI5AMPVAZGYQH54HMSOZ62","short_pith_number":"pith:VTJNFI5A","schema_version":"1.0","canonical_sha256":"acd2d2a3a063ea0c9b103f787649d9f6b1d3777b24765da17849f954757cef6a","source":{"kind":"arxiv","id":"2410.16946","version":1},"attestation_state":"computed","paper":{"title":"Self-Evolving Multi-Agent Collaboration Networks for Software Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.SE","authors_text":"Shuo Tang, Siheng Chen, Xiangrui Liu, Xinyu Zhu, Yaxin Du, Yuchen Hou, Yue Hu, Yuzhu Cai, Zijie Yu","submitted_at":"2024-10-22T12:20:23Z","abstract_excerpt":"LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the ne"},"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":"2410.16946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2024-10-22T12:20:23Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"d1e2c04663b2581cc6d26e7a49aa6446d27958ec9bcd7fe84601b8519cba28a1","abstract_canon_sha256":"c18b8f9849d58a097a000a08d0750a52a689a77159eba02b03afa5484eefa6af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:19.191116Z","signature_b64":"WUsLw9DehQb9pFxCcnk9yE1MnEkyENT0s8OanpfbIeCpoE6iXzBd9z+ibE42CnVGb5wja9IOz3Xy7xZo5SyxDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acd2d2a3a063ea0c9b103f787649d9f6b1d3777b24765da17849f954757cef6a","last_reissued_at":"2026-07-05T09:24:19.190618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:19.190618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Evolving Multi-Agent Collaboration Networks for Software Development","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.SE","authors_text":"Shuo Tang, Siheng Chen, Xiangrui Liu, Xinyu Zhu, Yaxin Du, Yuchen Hou, Yue Hu, Yuzhu Cai, Zijie Yu","submitted_at":"2024-10-22T12:20:23Z","abstract_excerpt":"LLM-driven multi-agent collaboration (MAC) systems have demonstrated impressive capabilities in automatic software development at the function level. However, their heavy reliance on human design limits their adaptability to the diverse demands of real-world software development. To address this limitation, we introduce EvoMAC, a novel self-evolving paradigm for MAC networks. Inspired by traditional neural network training, EvoMAC obtains text-based environmental feedback by verifying the MAC network's output against a target proxy and leverages a novel textual backpropagation to update the ne"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16946","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/2410.16946/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":"2410.16946","created_at":"2026-07-05T09:24:19.190678+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16946v1","created_at":"2026-07-05T09:24:19.190678+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16946","created_at":"2026-07-05T09:24:19.190678+00:00"},{"alias_kind":"pith_short_12","alias_value":"VTJNFI5AMPVA","created_at":"2026-07-05T09:24:19.190678+00:00"},{"alias_kind":"pith_short_16","alias_value":"VTJNFI5AMPVAZGYQ","created_at":"2026-07-05T09:24:19.190678+00:00"},{"alias_kind":"pith_short_8","alias_value":"VTJNFI5A","created_at":"2026-07-05T09:24:19.190678+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06786","citing_title":"From Agentic to Autogenic Network Management for AI-Native 6G and Beyond: A Standards Perspective","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2606.22385","citing_title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15245","citing_title":"Assistance to Autonomy: A Systematic Literature Review of Agentic AI across the Software Development Life Cycle","ref_index":12,"is_internal_anchor":false},{"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":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12943","citing_title":"Reinforced Collaboration in Multi-Agent Flow Networks","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12376","citing_title":"ProfiliTable: Profiling-Driven Tabular Data Processing via Agentic Workflows","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08769","citing_title":"EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10118","citing_title":"Plan in Sandbox, Navigate in Open Worlds: Learning Physics-Grounded Abstracted Experience for Embodied Navigation","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18133","citing_title":"Multi-Agent Systems: From Classical Paradigms to Large Foundation Model-Enabled Futures","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17503","citing_title":"SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62","json":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62.json","graph_json":"https://pith.science/api/pith-number/VTJNFI5AMPVAZGYQH54HMSOZ62/graph.json","events_json":"https://pith.science/api/pith-number/VTJNFI5AMPVAZGYQH54HMSOZ62/events.json","paper":"https://pith.science/paper/VTJNFI5A"},"agent_actions":{"view_html":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62","download_json":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62.json","view_paper":"https://pith.science/paper/VTJNFI5A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16946&json=true","fetch_graph":"https://pith.science/api/pith-number/VTJNFI5AMPVAZGYQH54HMSOZ62/graph.json","fetch_events":"https://pith.science/api/pith-number/VTJNFI5AMPVAZGYQH54HMSOZ62/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62/action/storage_attestation","attest_author":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62/action/author_attestation","sign_citation":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62/action/citation_signature","submit_replication":"https://pith.science/pith/VTJNFI5AMPVAZGYQH54HMSOZ62/action/replication_record"}},"created_at":"2026-07-05T09:24:19.190678+00:00","updated_at":"2026-07-05T09:24:19.190678+00:00"}