{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZJS7WHANETNIRUTJCKSYAPI6TW","short_pith_number":"pith:ZJS7WHAN","schema_version":"1.0","canonical_sha256":"ca65fb1c0d24da88d26912a5803d1e9dab3da6b31d7e7771e56754ceef6dae06","source":{"kind":"arxiv","id":"2510.07799","version":2},"attestation_state":"computed","paper":{"title":"Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Hanchen Jiang, Guancheng Wan, Kai-Wei Chang, Mengting Li, Sophia Yin, Wei Wang, Xiao Liang, Xinfeng Li, Ying Nian Wu, Yizhou Sun, Yuchen Wu","submitted_at":"2025-10-09T05:28:28Z","abstract_excerpt":"The efficiency of multi-agent systems driven by large language models (LLMs) largely hinges on their communication topology. However, designing an optimal topology is a non-trivial challenge, as it requires balancing competing objectives such as task performance, communication cost, and robustness. Existing frameworks often rely on static or hand-crafted topologies, which inherently fail to adapt to diverse task requirements, leading to either excessive token consumption for simple problems or performance bottlenecks for complex ones. To address this challenge, we introduce a novel generative "},"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":"2510.07799","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-09T05:28:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4a9bc6dad1311e2dc289ed4043ec377f3978cbaeb693d93bc2be516da1e33cd8","abstract_canon_sha256":"da0052b304a9c72368ee6681f3090f793bc0c34cdb25377c9fe62d77c5d48876"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:56.985680Z","signature_b64":"R/DZuE+TT1PctrX5FZwDjru5B27WKXtj1vHKNuPRlbN1E8L9CVZARUJ9yU6/lKawMyKu4uXyaXE4aTI2zf5nCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca65fb1c0d24da88d26912a5803d1e9dab3da6b31d7e7771e56754ceef6dae06","last_reissued_at":"2026-05-20T00:02:56.984827Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:56.984827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Eric Hanchen Jiang, Guancheng Wan, Kai-Wei Chang, Mengting Li, Sophia Yin, Wei Wang, Xiao Liang, Xinfeng Li, Ying Nian Wu, Yizhou Sun, Yuchen Wu","submitted_at":"2025-10-09T05:28:28Z","abstract_excerpt":"The efficiency of multi-agent systems driven by large language models (LLMs) largely hinges on their communication topology. However, designing an optimal topology is a non-trivial challenge, as it requires balancing competing objectives such as task performance, communication cost, and robustness. Existing frameworks often rely on static or hand-crafted topologies, which inherently fail to adapt to diverse task requirements, leading to either excessive token consumption for simple problems or performance bottlenecks for complex ones. To address this challenge, we introduce a novel generative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.07799","kind":"arxiv","version":2},"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/2510.07799/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":"2510.07799","created_at":"2026-05-20T00:02:56.984963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.07799v2","created_at":"2026-05-20T00:02:56.984963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.07799","created_at":"2026-05-20T00:02:56.984963+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJS7WHANETNI","created_at":"2026-05-20T00:02:56.984963+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJS7WHANETNIRUTJ","created_at":"2026-05-20T00:02:56.984963+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJS7WHAN","created_at":"2026-05-20T00:02:56.984963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.09104","citing_title":"Token Economics for LLM Agents: A Dual-View Study from Computing and Economics","ref_index":103,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09907","citing_title":"RADAR: Redundancy-Aware Diffusion for Multi-Agent Communication Structure Generation","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW","json":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW.json","graph_json":"https://pith.science/api/pith-number/ZJS7WHANETNIRUTJCKSYAPI6TW/graph.json","events_json":"https://pith.science/api/pith-number/ZJS7WHANETNIRUTJCKSYAPI6TW/events.json","paper":"https://pith.science/paper/ZJS7WHAN"},"agent_actions":{"view_html":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW","download_json":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW.json","view_paper":"https://pith.science/paper/ZJS7WHAN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.07799&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJS7WHANETNIRUTJCKSYAPI6TW/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJS7WHANETNIRUTJCKSYAPI6TW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW/action/storage_attestation","attest_author":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW/action/author_attestation","sign_citation":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW/action/citation_signature","submit_replication":"https://pith.science/pith/ZJS7WHANETNIRUTJCKSYAPI6TW/action/replication_record"}},"created_at":"2026-05-20T00:02:56.984963+00:00","updated_at":"2026-05-20T00:02:56.984963+00:00"}