{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PIICRFIM2JXAWJ4JDOXU5KV24S","short_pith_number":"pith:PIICRFIM","schema_version":"1.0","canonical_sha256":"7a1028950cd26e0b27891baf4eaabae4a486ad371c7b3886abfc191f6bc0451b","source":{"kind":"arxiv","id":"2605.26178","version":1},"attestation_state":"computed","paper":{"title":"ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Chang Liu, Guanjie Cheng, Naibo Wang, Qingyu Ma, Sai Liu, Xinkui Zhao, Yifan Zhang, Yueshen Xu, Zewen Lin","submitted_at":"2026-05-25T06:41:11Z","abstract_excerpt":"Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often misalign computational budgets with query difficulty. We propose \\textsc{ATOM}, an adaptive framework that generates budget-controllable collaboration graphs via a novel task-driven reinforcement learning paradigm. Inspired by atomic structures, \\textsc{ATOM} employs a nucleus-electron hierarchy: it maintains a stable, offline-learned collaboration backbone "},"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":"2605.26178","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MA","submitted_at":"2026-05-25T06:41:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"22585484e4c98177c36ad45a9fa1734886eb78c776a267bf21c9b8bf13c5dd53","abstract_canon_sha256":"5a19ea8e37f01944d6842bd975bc196e16cf04325abb68bb2458710e1bc38012"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T00:04:27.567546Z","signature_b64":"8wqwhkSX88uEqsEq6+GGWS13LKQHgJpYZW3GADbYyKGblU9BMEO/6aqGjjB6o3WKHGfR2XnTc2L1dup5HNLHDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a1028950cd26e0b27891baf4eaabae4a486ad371c7b3886abfc191f6bc0451b","last_reissued_at":"2026-05-27T00:04:27.566762Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T00:04:27.566762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.MA","authors_text":"Chang Liu, Guanjie Cheng, Naibo Wang, Qingyu Ma, Sai Liu, Xinkui Zhao, Yifan Zhang, Yueshen Xu, Zewen Lin","submitted_at":"2026-05-25T06:41:11Z","abstract_excerpt":"Large Language Model (LLM)-based multi-agent systems rely on optimized collaboration topologies to balance performance and communication costs. However, current methods struggle with the inherent stability-extensibility trade-off and often misalign computational budgets with query difficulty. We propose \\textsc{ATOM}, an adaptive framework that generates budget-controllable collaboration graphs via a novel task-driven reinforcement learning paradigm. Inspired by atomic structures, \\textsc{ATOM} employs a nucleus-electron hierarchy: it maintains a stable, offline-learned collaboration backbone "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26178","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/2605.26178/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":"2605.26178","created_at":"2026-05-27T00:04:27.566897+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26178v1","created_at":"2026-05-27T00:04:27.566897+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26178","created_at":"2026-05-27T00:04:27.566897+00:00"},{"alias_kind":"pith_short_12","alias_value":"PIICRFIM2JXA","created_at":"2026-05-27T00:04:27.566897+00:00"},{"alias_kind":"pith_short_16","alias_value":"PIICRFIM2JXAWJ4J","created_at":"2026-05-27T00:04:27.566897+00:00"},{"alias_kind":"pith_short_8","alias_value":"PIICRFIM","created_at":"2026-05-27T00:04:27.566897+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S","json":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S.json","graph_json":"https://pith.science/api/pith-number/PIICRFIM2JXAWJ4JDOXU5KV24S/graph.json","events_json":"https://pith.science/api/pith-number/PIICRFIM2JXAWJ4JDOXU5KV24S/events.json","paper":"https://pith.science/paper/PIICRFIM"},"agent_actions":{"view_html":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S","download_json":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S.json","view_paper":"https://pith.science/paper/PIICRFIM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26178&json=true","fetch_graph":"https://pith.science/api/pith-number/PIICRFIM2JXAWJ4JDOXU5KV24S/graph.json","fetch_events":"https://pith.science/api/pith-number/PIICRFIM2JXAWJ4JDOXU5KV24S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S/action/storage_attestation","attest_author":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S/action/author_attestation","sign_citation":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S/action/citation_signature","submit_replication":"https://pith.science/pith/PIICRFIM2JXAWJ4JDOXU5KV24S/action/replication_record"}},"created_at":"2026-05-27T00:04:27.566897+00:00","updated_at":"2026-05-27T00:04:27.566897+00:00"}