{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PBYT4ZYUXMIDKIPBJQWDOOSK4N","short_pith_number":"pith:PBYT4ZYU","schema_version":"1.0","canonical_sha256":"78713e6714bb103521e14c2c373a4ae375ce7b3298bb351da4f5d7540b58a6ce","source":{"kind":"arxiv","id":"2409.03215","version":1},"attestation_state":"computed","paper":{"title":"xLAM: A Family of Large Action Models to Empower AI Agent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshara Prabhakar, Caiming Xiong, Eric Hu, Haolin Chen, Huan Wang, Jianguo Zhang, Juan Carlos Niebles, Juntao Tan, Ming Zhu, Ran Xu, Rithesh Murthy, Shelby Heinecke, Shirley Kokane, Silvio Savarese, Thai Hoang, Tian Lan, Tulika Awalgaonkar, Weiran Yao, Yihao Feng, Zeyuan Chen, Zhiwei Liu, Zuxin Liu","submitted_at":"2024-09-05T03:22:22Z","abstract_excerpt":"Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protocols in this area. We introduce and publicly release xLAM, a series of large action models designed for AI agent tasks. The xLAM series includes five models with both dense and mixture-of-expert architectures, ranging from 1B to 8x22B parameters, trained using a scalable, flexible pipeline that unifie"},"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":"2409.03215","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T03:22:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"f57a1da2739ab7ac22d27ca2ca0fe9e4ae99ae144136b104ef251e223ebf4040","abstract_canon_sha256":"915156b5b28bdf2fe112f58189dab4ba0aaa345221466ac03b55bfa99d866691"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:27.742514Z","signature_b64":"7fYKxgNRlDBSWrf9kpDzV+9mEfjAKGL27lcmzn414rrfklH5qLN51oIPw/WVUswR4LQBRTBWr5fbKs+tPvt9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78713e6714bb103521e14c2c373a4ae375ce7b3298bb351da4f5d7540b58a6ce","last_reissued_at":"2026-07-05T09:03:27.742007Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:27.742007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"xLAM: A Family of Large Action Models to Empower AI Agent Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Akshara Prabhakar, Caiming Xiong, Eric Hu, Haolin Chen, Huan Wang, Jianguo Zhang, Juan Carlos Niebles, Juntao Tan, Ming Zhu, Ran Xu, Rithesh Murthy, Shelby Heinecke, Shirley Kokane, Silvio Savarese, Thai Hoang, Tian Lan, Tulika Awalgaonkar, Weiran Yao, Yihao Feng, Zeyuan Chen, Zhiwei Liu, Zuxin Liu","submitted_at":"2024-09-05T03:22:22Z","abstract_excerpt":"Autonomous agents powered by large language models (LLMs) have attracted significant research interest. However, the open-source community faces many challenges in developing specialized models for agent tasks, driven by the scarcity of high-quality agent datasets and the absence of standard protocols in this area. We introduce and publicly release xLAM, a series of large action models designed for AI agent tasks. The xLAM series includes five models with both dense and mixture-of-expert architectures, ranging from 1B to 8x22B parameters, trained using a scalable, flexible pipeline that unifie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03215","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/2409.03215/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":"2409.03215","created_at":"2026-07-05T09:03:27.742068+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.03215v1","created_at":"2026-07-05T09:03:27.742068+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03215","created_at":"2026-07-05T09:03:27.742068+00:00"},{"alias_kind":"pith_short_12","alias_value":"PBYT4ZYUXMID","created_at":"2026-07-05T09:03:27.742068+00:00"},{"alias_kind":"pith_short_16","alias_value":"PBYT4ZYUXMIDKIPB","created_at":"2026-07-05T09:03:27.742068+00:00"},{"alias_kind":"pith_short_8","alias_value":"PBYT4ZYU","created_at":"2026-07-05T09:03:27.742068+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03892","citing_title":"Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2509.18847","citing_title":"Failure Makes the Agent Stronger: Enhancing Accuracy through Structured Reflection for Reliable Tool Interactions","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2506.02153","citing_title":"Small Language Models are the Future of Agentic AI","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13958","citing_title":"ToolRL: Reward is All Tool Learning Needs","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07112","citing_title":"Switchcraft: AI Model Router for Agentic Tool Calling","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N","json":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N.json","graph_json":"https://pith.science/api/pith-number/PBYT4ZYUXMIDKIPBJQWDOOSK4N/graph.json","events_json":"https://pith.science/api/pith-number/PBYT4ZYUXMIDKIPBJQWDOOSK4N/events.json","paper":"https://pith.science/paper/PBYT4ZYU"},"agent_actions":{"view_html":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N","download_json":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N.json","view_paper":"https://pith.science/paper/PBYT4ZYU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.03215&json=true","fetch_graph":"https://pith.science/api/pith-number/PBYT4ZYUXMIDKIPBJQWDOOSK4N/graph.json","fetch_events":"https://pith.science/api/pith-number/PBYT4ZYUXMIDKIPBJQWDOOSK4N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N/action/storage_attestation","attest_author":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N/action/author_attestation","sign_citation":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N/action/citation_signature","submit_replication":"https://pith.science/pith/PBYT4ZYUXMIDKIPBJQWDOOSK4N/action/replication_record"}},"created_at":"2026-07-05T09:03:27.742068+00:00","updated_at":"2026-07-05T09:03:27.742068+00:00"}