{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ORW57WEI73PYP6BAL47S62TRAW","short_pith_number":"pith:ORW57WEI","schema_version":"1.0","canonical_sha256":"746ddfd888fedf87f8205f3f2f6a71059f4d25d5636cc656aa0edd50182c3313","source":{"kind":"arxiv","id":"2410.11782","version":3},"attestation_state":"computed","paper":{"title":"G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Dawei Cheng, Guancheng Wan, Guibin Zhang, Junfeng Fang, Kun Wang, Miao Yu, Tianlong Chen, Xiangguo Sun, Yanwei Yue","submitted_at":"2024-10-15T17:01:21Z","abstract_excerpt":"Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \\textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designe"},"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":"2410.11782","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2024-10-15T17:01:21Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f60a5f165202a5e2ef96b8b7c4708ddd58dda2993e0078d7ca48f6e56f0b1459","abstract_canon_sha256":"d045029316a1e2319f3d41e3fe32266b670f805be5854f6a92d90d22a73500ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:28.460603Z","signature_b64":"eIbgJ1mEuWxHmOz+kPDOJ53+0mOVrrIUwa8BriSytP4vlHLDl6NPCWdBDn8gxPZMYrtuggSeCYxWC2J36NhJDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"746ddfd888fedf87f8205f3f2f6a71059f4d25d5636cc656aa0edd50182c3313","last_reissued_at":"2026-07-05T10:10:28.460118Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:28.460118Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"G-Designer: Architecting Multi-agent Communication Topologies via Graph Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Dawei Cheng, Guancheng Wan, Guibin Zhang, Junfeng Fang, Kun Wang, Miao Yu, Tianlong Chen, Xiangguo Sun, Yanwei Yue","submitted_at":"2024-10-15T17:01:21Z","abstract_excerpt":"Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \\textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11782","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/2410.11782/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":"2410.11782","created_at":"2026-07-05T10:10:28.460174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11782v3","created_at":"2026-07-05T10:10:28.460174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11782","created_at":"2026-07-05T10:10:28.460174+00:00"},{"alias_kind":"pith_short_12","alias_value":"ORW57WEI73PY","created_at":"2026-07-05T10:10:28.460174+00:00"},{"alias_kind":"pith_short_16","alias_value":"ORW57WEI73PYP6BA","created_at":"2026-07-05T10:10:28.460174+00:00"},{"alias_kind":"pith_short_8","alias_value":"ORW57WEI","created_at":"2026-07-05T10:10:28.460174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06935","citing_title":"Mathematical methods of reinforcement learning","ref_index":114,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23664","citing_title":"MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22385","citing_title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","ref_index":85,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19758","citing_title":"SIGMA: Skill-Incidence Graphs for Compositional Multi-Agent Design","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20621","citing_title":"PEAR: Permutation-Equivariant Adaptive Routing Multi-Agent Debate","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01199","citing_title":"Can LLM Agents Sustain Long-Horizon Organizational Dynamics?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17361","citing_title":"MasFACT: Continual Multi-Agent Topology Learning via Geometry-Aware Posterior Transfer","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14483","citing_title":"LEMON: Learning Executable Multi-Agent Orchestration via Counterfactual Reinforcement Learning","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12513","citing_title":"SP-GCRL: Influence Maximization on Incomplete Social Graphs","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27691","citing_title":"When Agents Evolve, Institutions Follow","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08769","citing_title":"EvoMAS: Learning Execution-Time Workflows for Multi-Agent Systems","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08647","citing_title":"AgentCollabBench: Diagnosing When Good Agents Make Bad Collaborators","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05703","citing_title":"Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11378","citing_title":"From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05703","citing_title":"Active Learning for Communication Structure Optimization in LLM-Based Multi-Agent Systems","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22820","citing_title":"Complete Cyclic Subtask Graphs for Tool-Using LLM Agents: Flexibility, Cost, and Bottlenecks in Multi-Agent Workflows","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17503","citing_title":"SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02452","citing_title":"Position: How can Graphs Help Large Language Models?","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW","json":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW.json","graph_json":"https://pith.science/api/pith-number/ORW57WEI73PYP6BAL47S62TRAW/graph.json","events_json":"https://pith.science/api/pith-number/ORW57WEI73PYP6BAL47S62TRAW/events.json","paper":"https://pith.science/paper/ORW57WEI"},"agent_actions":{"view_html":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW","download_json":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW.json","view_paper":"https://pith.science/paper/ORW57WEI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11782&json=true","fetch_graph":"https://pith.science/api/pith-number/ORW57WEI73PYP6BAL47S62TRAW/graph.json","fetch_events":"https://pith.science/api/pith-number/ORW57WEI73PYP6BAL47S62TRAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW/action/storage_attestation","attest_author":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW/action/author_attestation","sign_citation":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW/action/citation_signature","submit_replication":"https://pith.science/pith/ORW57WEI73PYP6BAL47S62TRAW/action/replication_record"}},"created_at":"2026-07-05T10:10:28.460174+00:00","updated_at":"2026-07-05T10:10:28.460174+00:00"}