{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6PK7YWSAIPX7KSOGZL7JXFAGLL","short_pith_number":"pith:6PK7YWSA","schema_version":"1.0","canonical_sha256":"f3d5fc5a4043eff549c6cafe9b94065ac2c951535d0c0564fcf0183e0617471d","source":{"kind":"arxiv","id":"2606.21445","version":1},"attestation_state":"computed","paper":{"title":"AutoRAS: Learning Robust Agentic Systems with Primitive Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Congyu Guo, Guoshun Nan, Hua Wang, Jingfeng Zhang, Jingru Shan, Ji Zhang, Xuancheng Zhu, Yang Yue, Yuyang Ma, Zihan Dou","submitted_at":"2026-06-19T14:05:37Z","abstract_excerpt":"The automated design of agentic systems offers a promising pathway for scaling large language models (LLMs) beyond single-agent reasoning. While prior work has advanced task performance through handcrafted or automatically generated multi-agent workflows, robustness is often treated as an afterthought, leaving systems vulnerable to external adversaries and internal failures. We propose AutoRAS, a framework for the Automated design of Robust Agentic Systems. AutoRAS formulates system design as generating a sequence of symbolic primitives that jointly encode structural connectivity and behaviora"},"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":"2606.21445","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-19T14:05:37Z","cross_cats_sorted":[],"title_canon_sha256":"d0a68941f03a1d1f493a968c71ad41ff366a39963783189a0e08a9dab78bc5a7","abstract_canon_sha256":"44c9f07bb3ea36c1e2d2db7afb2074d9e02af096d1152aea4127f321f2ccce13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:10.605615Z","signature_b64":"x+csZAu5vCUiMt/dTOusoyg2tZonyvnb3byIgUbjUutNvgwkfT+6DBEhZQ+luEJu2IwS5aOR4kUTgR7jRFsLAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3d5fc5a4043eff549c6cafe9b94065ac2c951535d0c0564fcf0183e0617471d","last_reissued_at":"2026-06-23T01:13:10.605099Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:10.605099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AutoRAS: Learning Robust Agentic Systems with Primitive Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Congyu Guo, Guoshun Nan, Hua Wang, Jingfeng Zhang, Jingru Shan, Ji Zhang, Xuancheng Zhu, Yang Yue, Yuyang Ma, Zihan Dou","submitted_at":"2026-06-19T14:05:37Z","abstract_excerpt":"The automated design of agentic systems offers a promising pathway for scaling large language models (LLMs) beyond single-agent reasoning. While prior work has advanced task performance through handcrafted or automatically generated multi-agent workflows, robustness is often treated as an afterthought, leaving systems vulnerable to external adversaries and internal failures. We propose AutoRAS, a framework for the Automated design of Robust Agentic Systems. AutoRAS formulates system design as generating a sequence of symbolic primitives that jointly encode structural connectivity and behaviora"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21445","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/2606.21445/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":"2606.21445","created_at":"2026-06-23T01:13:10.605175+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21445v1","created_at":"2026-06-23T01:13:10.605175+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21445","created_at":"2026-06-23T01:13:10.605175+00:00"},{"alias_kind":"pith_short_12","alias_value":"6PK7YWSAIPX7","created_at":"2026-06-23T01:13:10.605175+00:00"},{"alias_kind":"pith_short_16","alias_value":"6PK7YWSAIPX7KSOG","created_at":"2026-06-23T01:13:10.605175+00:00"},{"alias_kind":"pith_short_8","alias_value":"6PK7YWSA","created_at":"2026-06-23T01:13:10.605175+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/6PK7YWSAIPX7KSOGZL7JXFAGLL","json":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL.json","graph_json":"https://pith.science/api/pith-number/6PK7YWSAIPX7KSOGZL7JXFAGLL/graph.json","events_json":"https://pith.science/api/pith-number/6PK7YWSAIPX7KSOGZL7JXFAGLL/events.json","paper":"https://pith.science/paper/6PK7YWSA"},"agent_actions":{"view_html":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL","download_json":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL.json","view_paper":"https://pith.science/paper/6PK7YWSA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21445&json=true","fetch_graph":"https://pith.science/api/pith-number/6PK7YWSAIPX7KSOGZL7JXFAGLL/graph.json","fetch_events":"https://pith.science/api/pith-number/6PK7YWSAIPX7KSOGZL7JXFAGLL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL/action/storage_attestation","attest_author":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL/action/author_attestation","sign_citation":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL/action/citation_signature","submit_replication":"https://pith.science/pith/6PK7YWSAIPX7KSOGZL7JXFAGLL/action/replication_record"}},"created_at":"2026-06-23T01:13:10.605175+00:00","updated_at":"2026-06-23T01:13:10.605175+00:00"}