{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P3UMIPJ2V6VUZPQKQYIFXUJWE2","short_pith_number":"pith:P3UMIPJ2","schema_version":"1.0","canonical_sha256":"7ee8c43d3aafab4cbe0a86105bd136268ed1bd52560d3c096037a5b8dab45428","source":{"kind":"arxiv","id":"2605.18703","version":1},"attestation_state":"computed","paper":{"title":"EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Baiyu Huang, Boyu Zhu, Chao Chen, Fei Mi, Heyuan Deng, Lifeng Shang, Mengyi Deng, Minrui Xu, Xiao Zhu, Xingshan Zeng, Yinhong Liu, Zhicheng Yang, Zhijiang Guo, Zhiwei Li, Zilin Wang","submitted_at":"2026-05-18T17:37:40Z","abstract_excerpt":"Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data that captures implicit human reasoning. Existing approaches depend on costly real-world APIs, hallucination-prone LLM simulators, or synthetic environments that are often single-turn or depend on pre-collected documents. Moreover, synthetic trajectories are frequently over-specified, resembling instruction sequences rather than natural human intents, reducing their effectivene"},"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":"2605.18703","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-18T17:37:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cc4a1b35d4c81b7863e41efeb942f15a823954787a504cabf3ba24e4e8b222ed","abstract_canon_sha256":"5ed7ceac898edd64b3449996fac6b42e7bf5256a4e6bab58c31e54765761e5ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:16.028403Z","signature_b64":"CzHCtcxQctherR+FwaE7OM8P7LnjziyjAn7UmVeCRj5Ou8bIP0ictGLziNBs8w+ZwwT+fkCLbfIsZ0N4ThajCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ee8c43d3aafab4cbe0a86105bd136268ed1bd52560d3c096037a5b8dab45428","last_reissued_at":"2026-05-20T00:06:16.027531Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:16.027531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Baiyu Huang, Boyu Zhu, Chao Chen, Fei Mi, Heyuan Deng, Lifeng Shang, Mengyi Deng, Minrui Xu, Xiao Zhu, Xingshan Zeng, Yinhong Liu, Zhicheng Yang, Zhijiang Guo, Zhiwei Li, Zilin Wang","submitted_at":"2026-05-18T17:37:40Z","abstract_excerpt":"Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execution environments and the scarcity of realistic training data that captures implicit human reasoning. Existing approaches depend on costly real-world APIs, hallucination-prone LLM simulators, or synthetic environments that are often single-turn or depend on pre-collected documents. Moreover, synthetic trajectories are frequently over-specified, resembling instruction sequences rather than natural human intents, reducing their effectivene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18703","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/2605.18703/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.073284Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"ed3685ad7a32c8e64d95fce366617e932b017a7d25fc35985e5942f8af28e60c"},"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":"2605.18703","created_at":"2026-05-20T00:06:16.027668+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18703v1","created_at":"2026-05-20T00:06:16.027668+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18703","created_at":"2026-05-20T00:06:16.027668+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3UMIPJ2V6VU","created_at":"2026-05-20T00:06:16.027668+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3UMIPJ2V6VUZPQK","created_at":"2026-05-20T00:06:16.027668+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3UMIPJ2","created_at":"2026-05-20T00:06:16.027668+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/P3UMIPJ2V6VUZPQKQYIFXUJWE2","json":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2.json","graph_json":"https://pith.science/api/pith-number/P3UMIPJ2V6VUZPQKQYIFXUJWE2/graph.json","events_json":"https://pith.science/api/pith-number/P3UMIPJ2V6VUZPQKQYIFXUJWE2/events.json","paper":"https://pith.science/paper/P3UMIPJ2"},"agent_actions":{"view_html":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2","download_json":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2.json","view_paper":"https://pith.science/paper/P3UMIPJ2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18703&json=true","fetch_graph":"https://pith.science/api/pith-number/P3UMIPJ2V6VUZPQKQYIFXUJWE2/graph.json","fetch_events":"https://pith.science/api/pith-number/P3UMIPJ2V6VUZPQKQYIFXUJWE2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2/action/storage_attestation","attest_author":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2/action/author_attestation","sign_citation":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2/action/citation_signature","submit_replication":"https://pith.science/pith/P3UMIPJ2V6VUZPQKQYIFXUJWE2/action/replication_record"}},"created_at":"2026-05-20T00:06:16.027668+00:00","updated_at":"2026-05-20T00:06:16.027668+00:00"}