{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WYIFL4NM456CFO2WA5Z2MCP4GZ","short_pith_number":"pith:WYIFL4NM","schema_version":"1.0","canonical_sha256":"b61055f1ace77c22bb560773a609fc364024a30828b40ce7ac019de5924229d2","source":{"kind":"arxiv","id":"2605.20190","version":1},"attestation_state":"computed","paper":{"title":"Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.AI","authors_text":"Huaxi Huang, Linyang Li, Liyuan Deng, Shujian Deng, Xiao Sun, Yilei Shi, Yongkang Chen, Yongkang Dai, Zhihang Zhong","submitted_at":"2026-04-01T14:14:09Z","abstract_excerpt":"Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optimization, Simulation, and Modeling Orchestration), a tool-augmented reinforcement learning (RL) framework that teaches LLMs to complete the closed-loop CAD-CAE process. Specifically, we cast CAD generation, CAE solving, result parsing, and geometry revision as an interactive RL environment, where an LLM learns to orchestrate external tools and revi"},"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":"2605.20190","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-04-01T14:14:09Z","cross_cats_sorted":["cs.GR"],"title_canon_sha256":"d404841a1b5feda6d09aa4a92370985a0059ed785f6af8e90071e60e99974c66","abstract_canon_sha256":"27ea7189738eae906f1305b8ad581f5683bd2793bb0353dcbc9036b48a45a984"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T00:04:20.396104Z","signature_b64":"e6+reFpVdIudg1JRJNzfyk09HC+4BPFak/cjevIN1p+L5pePpmPYkftlc/+Jfs/nj0UEuOvZ0teC1txs4zDCDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b61055f1ace77c22bb560773a609fc364024a30828b40ce7ac019de5924229d2","last_reissued_at":"2026-05-21T00:04:20.395430Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T00:04:20.395430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tool-Augmented Agent for Closed-loop Optimization,Simulation,and Modeling Orchestration","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.GR"],"primary_cat":"cs.AI","authors_text":"Huaxi Huang, Linyang Li, Liyuan Deng, Shujian Deng, Xiao Sun, Yilei Shi, Yongkang Chen, Yongkang Dai, Zhihang Zhong","submitted_at":"2026-04-01T14:14:09Z","abstract_excerpt":"Iterative industrial design-simulation optimization is bottlenecked by the CAD-CAE semantic gap: translating simulation feedback into valid geometric edits under diverse, coupled constraints. To fill this gap, we propose COSMO-Agent (Closed-loop Optimization, Simulation, and Modeling Orchestration), a tool-augmented reinforcement learning (RL) framework that teaches LLMs to complete the closed-loop CAD-CAE process. Specifically, we cast CAD generation, CAE solving, result parsing, and geometry revision as an interactive RL environment, where an LLM learns to orchestrate external tools and revi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20190","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/2605.20190/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":"2605.20190","created_at":"2026-05-21T00:04:20.395511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20190v1","created_at":"2026-05-21T00:04:20.395511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20190","created_at":"2026-05-21T00:04:20.395511+00:00"},{"alias_kind":"pith_short_12","alias_value":"WYIFL4NM456C","created_at":"2026-05-21T00:04:20.395511+00:00"},{"alias_kind":"pith_short_16","alias_value":"WYIFL4NM456CFO2W","created_at":"2026-05-21T00:04:20.395511+00:00"},{"alias_kind":"pith_short_8","alias_value":"WYIFL4NM","created_at":"2026-05-21T00:04:20.395511+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/WYIFL4NM456CFO2WA5Z2MCP4GZ","json":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ.json","graph_json":"https://pith.science/api/pith-number/WYIFL4NM456CFO2WA5Z2MCP4GZ/graph.json","events_json":"https://pith.science/api/pith-number/WYIFL4NM456CFO2WA5Z2MCP4GZ/events.json","paper":"https://pith.science/paper/WYIFL4NM"},"agent_actions":{"view_html":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ","download_json":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ.json","view_paper":"https://pith.science/paper/WYIFL4NM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20190&json=true","fetch_graph":"https://pith.science/api/pith-number/WYIFL4NM456CFO2WA5Z2MCP4GZ/graph.json","fetch_events":"https://pith.science/api/pith-number/WYIFL4NM456CFO2WA5Z2MCP4GZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ/action/storage_attestation","attest_author":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ/action/author_attestation","sign_citation":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ/action/citation_signature","submit_replication":"https://pith.science/pith/WYIFL4NM456CFO2WA5Z2MCP4GZ/action/replication_record"}},"created_at":"2026-05-21T00:04:20.395511+00:00","updated_at":"2026-05-21T00:04:20.395511+00:00"}