{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DNEEVNA2LZGHCVU7FKIZEZADN6","short_pith_number":"pith:DNEEVNA2","schema_version":"1.0","canonical_sha256":"1b484ab41a5e4c71569f2a919264036f92c031473f55c4fbf1c12644044eb221","source":{"kind":"arxiv","id":"2504.03561","version":3},"attestation_state":"computed","paper":{"title":"SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MA"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Huajun Chen, Jialong Wu, Ningyu Zhang, Pengjun Xie, Runnan Fang, Shuofei Qiao, Xiaobin Wang, Yong Jiang, Yuan Liang, Zekun Xi","submitted_at":"2025-04-04T16:10:57Z","abstract_excerpt":"In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effective"},"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":"2504.03561","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-04T16:10:57Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG","cs.MA"],"title_canon_sha256":"a471d51fb48cc30ed049d47ff820ec85408e36c0b3bddf0b7471f1deebd04a95","abstract_canon_sha256":"bcc69a74385409d88db028de58897a53634f7fcd6a0387ca0c913d6b116ad03f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:23.582531Z","signature_b64":"mhCGLiGA+YWg22QCG/gPdz2mRVjMu3DQIMrNkUa+74GDrqr3yUw+6C57C0GepMVgvHGPe26nFIsbHDTjJLrqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b484ab41a5e4c71569f2a919264036f92c031473f55c4fbf1c12644044eb221","last_reissued_at":"2026-07-05T11:13:23.582026Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:23.582026Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SynWorld: Virtual Scenario Synthesis for Agentic Action Knowledge Refinement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG","cs.MA"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Huajun Chen, Jialong Wu, Ningyu Zhang, Pengjun Xie, Runnan Fang, Shuofei Qiao, Xiaobin Wang, Yong Jiang, Yuan Liang, Zekun Xi","submitted_at":"2025-04-04T16:10:57Z","abstract_excerpt":"In the interaction between agents and their environments, agents expand their capabilities by planning and executing actions. However, LLM-based agents face substantial challenges when deployed in novel environments or required to navigate unconventional action spaces. To empower agents to autonomously explore environments, optimize workflows, and enhance their understanding of actions, we propose SynWorld, a framework that allows agents to synthesize possible scenarios with multi-step action invocation within the action space and perform Monte Carlo Tree Search (MCTS) exploration to effective"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.03561","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/2504.03561/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":"2504.03561","created_at":"2026-07-05T11:13:23.582088+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.03561v3","created_at":"2026-07-05T11:13:23.582088+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.03561","created_at":"2026-07-05T11:13:23.582088+00:00"},{"alias_kind":"pith_short_12","alias_value":"DNEEVNA2LZGH","created_at":"2026-07-05T11:13:23.582088+00:00"},{"alias_kind":"pith_short_16","alias_value":"DNEEVNA2LZGHCVU7","created_at":"2026-07-05T11:13:23.582088+00:00"},{"alias_kind":"pith_short_8","alias_value":"DNEEVNA2","created_at":"2026-07-05T11:13:23.582088+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11470","citing_title":"The Periodic Table of LLM Reasoning: A Structured Survey of Reasoning Paradigms, Methods, and Failure Modes","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6","json":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6.json","graph_json":"https://pith.science/api/pith-number/DNEEVNA2LZGHCVU7FKIZEZADN6/graph.json","events_json":"https://pith.science/api/pith-number/DNEEVNA2LZGHCVU7FKIZEZADN6/events.json","paper":"https://pith.science/paper/DNEEVNA2"},"agent_actions":{"view_html":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6","download_json":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6.json","view_paper":"https://pith.science/paper/DNEEVNA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.03561&json=true","fetch_graph":"https://pith.science/api/pith-number/DNEEVNA2LZGHCVU7FKIZEZADN6/graph.json","fetch_events":"https://pith.science/api/pith-number/DNEEVNA2LZGHCVU7FKIZEZADN6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6/action/storage_attestation","attest_author":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6/action/author_attestation","sign_citation":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6/action/citation_signature","submit_replication":"https://pith.science/pith/DNEEVNA2LZGHCVU7FKIZEZADN6/action/replication_record"}},"created_at":"2026-07-05T11:13:23.582088+00:00","updated_at":"2026-07-05T11:13:23.582088+00:00"}