{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X4FQ3F2DOX5JR3DUPN7KRO4DRK","short_pith_number":"pith:X4FQ3F2D","schema_version":"1.0","canonical_sha256":"bf0b0d974375fa98ec747b7ea8bb838a954b960714ee72d3cc479ecf437651bf","source":{"kind":"arxiv","id":"2505.23187","version":1},"attestation_state":"computed","paper":{"title":"Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Chen Qian, Lei Han, Maosong Sun, Ruijie Shi, Weichuan Liu, Weize Chen, Xuantang Xiong, Ye Tian, Yilong Li, Yufan Dang, Yu Xia, Zhiyuan Liu, Zihao Xie, Ziming You","submitted_at":"2025-05-29T07:24:37Z","abstract_excerpt":"Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation, resulting in redundant computations and limited generalization across structurally similar tasks. To address this, we introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation. We model the task-solving workflow on a graph-structured multi-agent col"},"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":"2505.23187","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-29T07:24:37Z","cross_cats_sorted":["cs.AI","cs.MA"],"title_canon_sha256":"d6924a9656af8df05377c64383affe8c283d7fcbaa7ff9eb3ac497a02eb9462c","abstract_canon_sha256":"ca6195acfe916bf89df39802bec471e5c99eeb6736ca5f06daf809bf73f6f9e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:11:57.198090Z","signature_b64":"ioFJWg/wXH4dsrvdkXt5Q3M5xUVawaPPJa5ZI9iwOv+ibQdMMsZP79t+JJxDyzEzZJYj7/PBeaIWo5bTfpd5DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf0b0d974375fa98ec747b7ea8bb838a954b960714ee72d3cc479ecf437651bf","last_reissued_at":"2026-07-05T11:11:57.197586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:11:57.197586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MA"],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Chen Qian, Lei Han, Maosong Sun, Ruijie Shi, Weichuan Liu, Weize Chen, Xuantang Xiong, Ye Tian, Yilong Li, Yufan Dang, Yu Xia, Zhiyuan Liu, Zihao Xie, Ziming You","submitted_at":"2025-05-29T07:24:37Z","abstract_excerpt":"Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation, resulting in redundant computations and limited generalization across structurally similar tasks. To address this, we introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation. We model the task-solving workflow on a graph-structured multi-agent col"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.23187","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/2505.23187/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":"2505.23187","created_at":"2026-07-05T11:11:57.197644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.23187v1","created_at":"2026-07-05T11:11:57.197644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.23187","created_at":"2026-07-05T11:11:57.197644+00:00"},{"alias_kind":"pith_short_12","alias_value":"X4FQ3F2DOX5J","created_at":"2026-07-05T11:11:57.197644+00:00"},{"alias_kind":"pith_short_16","alias_value":"X4FQ3F2DOX5JR3DU","created_at":"2026-07-05T11:11:57.197644+00:00"},{"alias_kind":"pith_short_8","alias_value":"X4FQ3F2D","created_at":"2026-07-05T11:11:57.197644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29790","citing_title":"Evolve as a Team: Collaborative Self-Evolution for LLM-based Multi-Agent Systems","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00756","citing_title":"CoMIC: Collaborative Memory and Insights Circulation for Long-Horizon LLM Agents in Cloud-Edge Systems","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK","json":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK.json","graph_json":"https://pith.science/api/pith-number/X4FQ3F2DOX5JR3DUPN7KRO4DRK/graph.json","events_json":"https://pith.science/api/pith-number/X4FQ3F2DOX5JR3DUPN7KRO4DRK/events.json","paper":"https://pith.science/paper/X4FQ3F2D"},"agent_actions":{"view_html":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK","download_json":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK.json","view_paper":"https://pith.science/paper/X4FQ3F2D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.23187&json=true","fetch_graph":"https://pith.science/api/pith-number/X4FQ3F2DOX5JR3DUPN7KRO4DRK/graph.json","fetch_events":"https://pith.science/api/pith-number/X4FQ3F2DOX5JR3DUPN7KRO4DRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK/action/storage_attestation","attest_author":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK/action/author_attestation","sign_citation":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK/action/citation_signature","submit_replication":"https://pith.science/pith/X4FQ3F2DOX5JR3DUPN7KRO4DRK/action/replication_record"}},"created_at":"2026-07-05T11:11:57.197644+00:00","updated_at":"2026-07-05T11:11:57.197644+00:00"}