{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:77AQ2MJW2OLEV5XCJEX2Y7Y5HR","short_pith_number":"pith:77AQ2MJW","schema_version":"1.0","canonical_sha256":"ffc10d3136d3964af6e2492fac7f1d3c410cc8fece13c221e36a46ba314f4633","source":{"kind":"arxiv","id":"2607.17528","version":1},"attestation_state":"computed","paper":{"title":"Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cheng Zhuo, Chenyi Wen, Jinyuan Deng, Tianyu Xing, Xufeng Wei, Zhengrui Chen","submitted_at":"2026-07-20T04:08:06Z","abstract_excerpt":"LLM-driven agent systems have emerged as a promising paradigm for electronic design automation (EDA), demonstrating strong potential for automating complex design workflows. However, existing evaluations primarily examine individual language models on isolated EDA tasks, providing limited insight into how different agent systems perform across complete EDA flows. In this work, we present FluxBench, a systematic evaluation of AI agents on end-to-end EDA workflows under unified prompts, tool environments, and technology library settings. Our evaluation covers representative scenarios, including "},"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":"2607.17528","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-20T04:08:06Z","cross_cats_sorted":["cs.AR","cs.LG"],"title_canon_sha256":"75d6a1fc4ce9b8f2087c93907ae35178c594869878c366ca70b6edc194ef31cc","abstract_canon_sha256":"85ed2631faf575e1543ea991b6de4c73004888a9c33bba3683d7fce1daadac58"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:50.641075Z","signature_b64":"rVo6QjRLCZfWVQPa9Bwvyy5apEWqryM2ucEAF9Wyfdtbge6+S8GUitJdeLzi9xAbSYkmbU1Pf0b6CYqAG1FkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffc10d3136d3964af6e2492fac7f1d3c410cc8fece13c221e36a46ba314f4633","last_reissued_at":"2026-07-21T01:21:50.640176Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:50.640176Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Can AI Agents Really Complete RTL-to-GDS? Lessons from Benchmarking Tool-Interactive EDA Workflows","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AR","cs.LG"],"primary_cat":"cs.AI","authors_text":"Cheng Zhuo, Chenyi Wen, Jinyuan Deng, Tianyu Xing, Xufeng Wei, Zhengrui Chen","submitted_at":"2026-07-20T04:08:06Z","abstract_excerpt":"LLM-driven agent systems have emerged as a promising paradigm for electronic design automation (EDA), demonstrating strong potential for automating complex design workflows. However, existing evaluations primarily examine individual language models on isolated EDA tasks, providing limited insight into how different agent systems perform across complete EDA flows. In this work, we present FluxBench, a systematic evaluation of AI agents on end-to-end EDA workflows under unified prompts, tool environments, and technology library settings. Our evaluation covers representative scenarios, including "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17528","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/2607.17528/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":"2607.17528","created_at":"2026-07-21T01:21:50.640614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.17528v1","created_at":"2026-07-21T01:21:50.640614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17528","created_at":"2026-07-21T01:21:50.640614+00:00"},{"alias_kind":"pith_short_12","alias_value":"77AQ2MJW2OLE","created_at":"2026-07-21T01:21:50.640614+00:00"},{"alias_kind":"pith_short_16","alias_value":"77AQ2MJW2OLEV5XC","created_at":"2026-07-21T01:21:50.640614+00:00"},{"alias_kind":"pith_short_8","alias_value":"77AQ2MJW","created_at":"2026-07-21T01:21:50.640614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03738","citing_title":"AgenticECO: An Agentic Framework for ECO on 3D Integrated Circuits","ref_index":2026,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR","json":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR.json","graph_json":"https://pith.science/api/pith-number/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/graph.json","events_json":"https://pith.science/api/pith-number/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/events.json","paper":"https://pith.science/paper/77AQ2MJW"},"agent_actions":{"view_html":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR","download_json":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR.json","view_paper":"https://pith.science/paper/77AQ2MJW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.17528&json=true","fetch_graph":"https://pith.science/api/pith-number/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/graph.json","fetch_events":"https://pith.science/api/pith-number/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/action/storage_attestation","attest_author":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/action/author_attestation","sign_citation":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/action/citation_signature","submit_replication":"https://pith.science/pith/77AQ2MJW2OLEV5XCJEX2Y7Y5HR/action/replication_record"}},"created_at":"2026-07-21T01:21:50.640614+00:00","updated_at":"2026-07-21T01:21:50.640614+00:00"}