{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:OBNTXM2KUYIYNT3MAKJ3O5FODY","short_pith_number":"pith:OBNTXM2K","schema_version":"1.0","canonical_sha256":"705b3bb34aa61186cf6c0293b774ae1e050a29a29b48746a618575cc9f009e5c","source":{"kind":"arxiv","id":"2602.10090","version":3},"attestation_state":"computed","paper":{"title":"Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Boyi Liu, Canwen Xu, Huaxiu Yao, Siwei Han, Yite Wang, Yuxiong He, Zhaoyang Wang, Zhewei Yao","submitted_at":"2026-02-10T18:55:41Z","abstract_excerpt":"Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments. In this paper, we propose Agent World Model (AWM), a fully synthetic environment generation pipeline. Using this pipeline, we scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets and obtain high-quality observations. Notably, these environments are code-driven and backed by databases, providing more reliab"},"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":"2602.10090","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-02-10T18:55:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8254bc3541154d57427099b6bf6bb3b79d0157356c5d1a7d16da85e02d2802d0","abstract_canon_sha256":"bf310f2ce47a68cd1a4ef670ef97c06f8aa861accc7df047dbf490170795e3c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:02:32.120421Z","signature_b64":"t6iqHZ5VCxS6XU8N8yibReXyO4TddLExxViDjf/vTBRIiZFrzTN776BmYjG/vkqY/cJjHMkJF/PDyH9+fIw/Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"705b3bb34aa61186cf6c0293b774ae1e050a29a29b48746a618575cc9f009e5c","last_reissued_at":"2026-05-26T01:02:32.119579Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:02:32.119579Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent World Model: Infinity Synthetic Environments for Agentic Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Boyi Liu, Canwen Xu, Huaxiu Yao, Siwei Han, Yite Wang, Yuxiong He, Zhaoyang Wang, Zhewei Yao","submitted_at":"2026-02-10T18:55:41Z","abstract_excerpt":"Recent advances in large language model (LLM) have empowered autonomous agents to perform multi-turn interactions with tools and environments. However, scaling such agent training is limited by the lack of diverse and reliable environments. In this paper, we propose Agent World Model (AWM), a fully synthetic environment generation pipeline. Using this pipeline, we scale to 1,000 environments covering everyday scenarios, in which agents can interact with rich toolsets and obtain high-quality observations. Notably, these environments are code-driven and backed by databases, providing more reliab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.10090","kind":"arxiv","version":3},"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/2602.10090/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":"2602.10090","created_at":"2026-05-26T01:02:32.119687+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.10090v3","created_at":"2026-05-26T01:02:32.119687+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.10090","created_at":"2026-05-26T01:02:32.119687+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBNTXM2KUYIY","created_at":"2026-05-26T01:02:32.119687+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBNTXM2KUYIYNT3M","created_at":"2026-05-26T01:02:32.119687+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBNTXM2K","created_at":"2026-05-26T01:02:32.119687+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":131,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19769","citing_title":"OpenComputer: Verifiable Software Worlds for Computer-Use Agents","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09131","citing_title":"MCP-Cosmos: World Model-Augmented Agents for Complex Task Execution in MCP Environments","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18543","citing_title":"ClawEnvKit: Automatic Environment Generation for Claw-Like Agents","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02913","citing_title":"Generate, Filter, Control, Replay: A Comprehensive Survey of Rollout Strategies for LLM Reinforcement Learning","ref_index":125,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17739","citing_title":"Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18292","citing_title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","ref_index":101,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY","json":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY.json","graph_json":"https://pith.science/api/pith-number/OBNTXM2KUYIYNT3MAKJ3O5FODY/graph.json","events_json":"https://pith.science/api/pith-number/OBNTXM2KUYIYNT3MAKJ3O5FODY/events.json","paper":"https://pith.science/paper/OBNTXM2K"},"agent_actions":{"view_html":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY","download_json":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY.json","view_paper":"https://pith.science/paper/OBNTXM2K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.10090&json=true","fetch_graph":"https://pith.science/api/pith-number/OBNTXM2KUYIYNT3MAKJ3O5FODY/graph.json","fetch_events":"https://pith.science/api/pith-number/OBNTXM2KUYIYNT3MAKJ3O5FODY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY/action/storage_attestation","attest_author":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY/action/author_attestation","sign_citation":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY/action/citation_signature","submit_replication":"https://pith.science/pith/OBNTXM2KUYIYNT3MAKJ3O5FODY/action/replication_record"}},"created_at":"2026-05-26T01:02:32.119687+00:00","updated_at":"2026-05-26T01:02:32.119687+00:00"}