{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DSIAQX4DRUJBJIIG2OMCATKTHK","short_pith_number":"pith:DSIAQX4D","schema_version":"1.0","canonical_sha256":"1c90085f838d1214a106d398204d533aacd38fef282cde9cf57eaec03bacde0b","source":{"kind":"arxiv","id":"2310.02170","version":2},"attestation_state":"computed","paper":{"title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Diyi Yang, Peng Li, Yang Liu, Yanzhe Zhang, Zijun Liu","submitted_at":"2023-10-03T16:05:48Z","abstract_excerpt":"Recent studies show that collaborating multiple large language model (LLM) powered agents is a promising way for task solving. However, current approaches are constrained by using a fixed number of agents and static communication structures. In this work, we propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($\\textbf{DyLAN}$) for LLM-powered agent collaboration, operating a two-stage paradigm: (1) Team Optimization and"},"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":"2310.02170","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-03T16:05:48Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"47e087dac7dde4b5c95d30d8583cdfc457ec61b9787ac3a0361faec1c6e85eaf","abstract_canon_sha256":"0bb77c4988e3275942ed9de187f96d2eb9591ecbb823cd6aee94aac34a5f9d0e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T20:59:08.978518Z","signature_b64":"BF2T2t+qeSo0o9UnFdWooG/0yZcMxV7ttMjTYsnb03TAmg/dGgV9K42+H17gGoZXEhGDqoY49tf3/PSIQiPzCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c90085f838d1214a106d398204d533aacd38fef282cde9cf57eaec03bacde0b","last_reissued_at":"2026-05-21T20:59:08.975473Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T20:59:08.975473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Diyi Yang, Peng Li, Yang Liu, Yanzhe Zhang, Zijun Liu","submitted_at":"2023-10-03T16:05:48Z","abstract_excerpt":"Recent studies show that collaborating multiple large language model (LLM) powered agents is a promising way for task solving. However, current approaches are constrained by using a fixed number of agents and static communication structures. In this work, we propose automatically selecting a team of agents from candidates to collaborate in a dynamic communication structure toward different tasks and domains. Specifically, we build a framework named Dynamic LLM-Powered Agent Network ($\\textbf{DyLAN}$) for LLM-powered agent collaboration, operating a two-stage paradigm: (1) Team Optimization and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02170","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/2310.02170/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":"2310.02170","created_at":"2026-05-21T20:59:08.975593+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02170v2","created_at":"2026-05-21T20:59:08.975593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02170","created_at":"2026-05-21T20:59:08.975593+00:00"},{"alias_kind":"pith_short_12","alias_value":"DSIAQX4DRUJB","created_at":"2026-05-21T20:59:08.975593+00:00"},{"alias_kind":"pith_short_16","alias_value":"DSIAQX4DRUJBJIIG","created_at":"2026-05-21T20:59:08.975593+00:00"},{"alias_kind":"pith_short_8","alias_value":"DSIAQX4D","created_at":"2026-05-21T20:59:08.975593+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2504.02181","citing_title":"A Survey of Scaling in Large Language Model Reasoning","ref_index":120,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22721","citing_title":"Self-Evolving Multi-Agent Systems via Decentralized Memory","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2510.07799","citing_title":"Dynamic Generation of Multi-LLM Agents Communication Topologies with Graph Diffusion Models","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20425","citing_title":"AgentCo-op: Retrieval-Based Synthesis of Interoperable Multi-Agent Workflows","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15706","citing_title":"Differentiable Mixture-of-Agents Incentivizes Swarm Intelligence of Large Language Models","ref_index":89,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17359","citing_title":"Learning Transferable Topology Priors for Multi-Agent LLM Collaboration Across Domains","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19418","citing_title":"Conflict-Resilient Multi-Agent Reasoning via Signed Graph Modeling","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2404.11584","citing_title":"The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2406.20094","citing_title":"Scaling Synthetic Data Creation with 1,000,000,000 Personas","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2408.08435","citing_title":"Automated Design of Agentic Systems","ref_index":175,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12943","citing_title":"Reinforced Collaboration in Multi-Agent Flow Networks","ref_index":22,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02770","citing_title":"Improving Role Consistency in Multi-Agent Collaboration via Quantitative Role Clarity","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02674","citing_title":"Do Agent Societies Develop Intellectual Elites? The Hidden Power Laws of Collective Cognition in LLM Multi-Agent Systems","ref_index":36,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03809","citing_title":"Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27616","citing_title":"RoadMapper: A Multi-Agent System for Roadmap Generation of Solving Complex Research Problems","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08533","citing_title":"Human-LLM Dialogue Improves Diagnostic Accuracy in Emergency Care","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2402.01680","citing_title":"Large Language Model based Multi-Agents: A Survey of Progress and Challenges","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09278","citing_title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22577","citing_title":"QuantClaw: Precision Where It Matters for OpenClaw","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22446","citing_title":"From Skills to Talent: Organising Heterogeneous Agents as a Real-World Company","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10923","citing_title":"Mem$^2$Evolve: Towards Self-Evolving Agents via Co-Evolutionary Capability Expansion and Experience Distillation","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17503","citing_title":"SkillGraph: Self-Evolving Multi-Agent Collaboration with Multimodal Graph Topology","ref_index":29,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK","json":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK.json","graph_json":"https://pith.science/api/pith-number/DSIAQX4DRUJBJIIG2OMCATKTHK/graph.json","events_json":"https://pith.science/api/pith-number/DSIAQX4DRUJBJIIG2OMCATKTHK/events.json","paper":"https://pith.science/paper/DSIAQX4D"},"agent_actions":{"view_html":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK","download_json":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK.json","view_paper":"https://pith.science/paper/DSIAQX4D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02170&json=true","fetch_graph":"https://pith.science/api/pith-number/DSIAQX4DRUJBJIIG2OMCATKTHK/graph.json","fetch_events":"https://pith.science/api/pith-number/DSIAQX4DRUJBJIIG2OMCATKTHK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK/action/storage_attestation","attest_author":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK/action/author_attestation","sign_citation":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK/action/citation_signature","submit_replication":"https://pith.science/pith/DSIAQX4DRUJBJIIG2OMCATKTHK/action/replication_record"}},"created_at":"2026-05-21T20:59:08.975593+00:00","updated_at":"2026-05-21T20:59:08.975593+00:00"}