{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UZNBG3C24YSEJAT5J4ZGONGQSE","short_pith_number":"pith:UZNBG3C2","schema_version":"1.0","canonical_sha256":"a65a136c5ae62444827d4f326734d0913e8184b3e796d06ff7752c653c6b7064","source":{"kind":"arxiv","id":"2509.13557","version":7},"attestation_state":"computed","paper":{"title":"MACO: A Multi-Agent LLM Framework for Automated CGRA Hardware/Software Co-Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Cheng Tan, Deepak Patil, Jeff Zhang, Mahathi Krishna, Qing Zhong, Yuqi Sun, Zesong Jiang","submitted_at":"2025-09-16T21:52:04Z","abstract_excerpt":"Designing optimal Coarse-Grained Reconfigurable Arrays (CGRAs) requires navigating a vast, interdependent hardware/software space bottlenecked by costly manual iteration. We present MACO, an open-source, multi-agent LLM framework that automates CGRA HW/SW co-design. MACO decomposes the design loop into four collaborative stages, HW/SW Co-design, Error Correction, Best-Design Selection, and Evaluation & Feedback, to iteratively optimize power, performance, and area (PPA). To accelerate convergence and efficiently traverse the design space, MACO introduces an exponentially decaying exploration s"},"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":"2509.13557","kind":"arxiv","version":7},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-09-16T21:52:04Z","cross_cats_sorted":[],"title_canon_sha256":"3ac219af052563e5e3bbd3c1bb09c3819c68586f7d97f217d1b75493cd979fe0","abstract_canon_sha256":"60ea2b78dba665b8688f96733bf89cb55ab048e2db671a158a57b864c9147847"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:33.569379Z","signature_b64":"Y5+SEFZNt7dDlYpXSp+SFo0AvbYTHBorJalU3mLz7LA5KiEfVHF0BlgU/+WzYC/BvEULMwCwd8gPPPj9TlagCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a65a136c5ae62444827d4f326734d0913e8184b3e796d06ff7752c653c6b7064","last_reissued_at":"2026-06-02T01:03:33.568792Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:33.568792Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MACO: A Multi-Agent LLM Framework for Automated CGRA Hardware/Software Co-Design","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Cheng Tan, Deepak Patil, Jeff Zhang, Mahathi Krishna, Qing Zhong, Yuqi Sun, Zesong Jiang","submitted_at":"2025-09-16T21:52:04Z","abstract_excerpt":"Designing optimal Coarse-Grained Reconfigurable Arrays (CGRAs) requires navigating a vast, interdependent hardware/software space bottlenecked by costly manual iteration. We present MACO, an open-source, multi-agent LLM framework that automates CGRA HW/SW co-design. MACO decomposes the design loop into four collaborative stages, HW/SW Co-design, Error Correction, Best-Design Selection, and Evaluation & Feedback, to iteratively optimize power, performance, and area (PPA). To accelerate convergence and efficiently traverse the design space, MACO introduces an exponentially decaying exploration s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.13557","kind":"arxiv","version":7},"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/2509.13557/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":"2509.13557","created_at":"2026-06-02T01:03:33.568853+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.13557v7","created_at":"2026-06-02T01:03:33.568853+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.13557","created_at":"2026-06-02T01:03:33.568853+00:00"},{"alias_kind":"pith_short_12","alias_value":"UZNBG3C24YSE","created_at":"2026-06-02T01:03:33.568853+00:00"},{"alias_kind":"pith_short_16","alias_value":"UZNBG3C24YSEJAT5","created_at":"2026-06-02T01:03:33.568853+00:00"},{"alias_kind":"pith_short_8","alias_value":"UZNBG3C2","created_at":"2026-06-02T01:03:33.568853+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/UZNBG3C24YSEJAT5J4ZGONGQSE","json":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE.json","graph_json":"https://pith.science/api/pith-number/UZNBG3C24YSEJAT5J4ZGONGQSE/graph.json","events_json":"https://pith.science/api/pith-number/UZNBG3C24YSEJAT5J4ZGONGQSE/events.json","paper":"https://pith.science/paper/UZNBG3C2"},"agent_actions":{"view_html":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE","download_json":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE.json","view_paper":"https://pith.science/paper/UZNBG3C2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.13557&json=true","fetch_graph":"https://pith.science/api/pith-number/UZNBG3C24YSEJAT5J4ZGONGQSE/graph.json","fetch_events":"https://pith.science/api/pith-number/UZNBG3C24YSEJAT5J4ZGONGQSE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE/action/storage_attestation","attest_author":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE/action/author_attestation","sign_citation":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE/action/citation_signature","submit_replication":"https://pith.science/pith/UZNBG3C24YSEJAT5J4ZGONGQSE/action/replication_record"}},"created_at":"2026-06-02T01:03:33.568853+00:00","updated_at":"2026-06-02T01:03:33.568853+00:00"}