{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YBU3KTZLL3OZCQHKW5W3QLOMPH","short_pith_number":"pith:YBU3KTZL","schema_version":"1.0","canonical_sha256":"c069b54f2b5edd9140eab76db82dcc79d4553d2ead824d109e921cb0618e2606","source":{"kind":"arxiv","id":"2605.24598","version":1},"attestation_state":"computed","paper":{"title":"Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Chengfei Lv, Fan Xie, Jing Yang, Mengxue Hu, Wenjun Zhu, Xiaoyi Fan, Yuxin Zhang, Zhe Chen, Zheng Lin, Zhiwen Chen, Zihan Fang","submitted_at":"2026-05-23T14:29:33Z","abstract_excerpt":"Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achiev"},"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":"2605.24598","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-23T14:29:33Z","cross_cats_sorted":["cs.MA"],"title_canon_sha256":"d5282b955c51bcbaaa2b7dd915b560e205823a56c7c0185fe283019c044bc639","abstract_canon_sha256":"72801b3f5b15cb1d51193d790e0e6c95afd411c24d6b1f5248acfa8ee9f70719"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:48.321383Z","signature_b64":"F/k2OskzP0tHlSKq2x1QR9ROmeQQs4zhl55oLnqcJQfoaZH4Sm/MOJ2jIPZo1tz2o2GNw5dT2r8DUS+286gaAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c069b54f2b5edd9140eab76db82dcc79d4553d2ead824d109e921cb0618e2606","last_reissued_at":"2026-05-26T01:03:48.320524Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:48.320524Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hera: Learning Long-Horizon Coordination for Device-Cloud Collaborative LLM Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MA"],"primary_cat":"cs.AI","authors_text":"Chengfei Lv, Fan Xie, Jing Yang, Mengxue Hu, Wenjun Zhu, Xiaoyi Fan, Yuxin Zhang, Zhe Chen, Zheng Lin, Zhiwen Chen, Zihan Fang","submitted_at":"2026-05-23T14:29:33Z","abstract_excerpt":"Large language model (LLM) agents excel at solving complex long-horizon tasks through autonomous interaction with environments. However, their real-world deployment faces a fundamental device--cloud dilemma: on-device models are efficient but often brittle, while cloud models are stronger but costly in computation. State-of-the-art LLM device--cloud routers usually make coarse task-level decisions, which cannot adapt to the changing difficulty of multi-step agent interactions. To address this issue, we present Hera, a step-level device--cloud LLM agent coordinator for long-horizon tasks achiev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.24598","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/2605.24598/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":"2605.24598","created_at":"2026-05-26T01:03:48.320677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.24598v1","created_at":"2026-05-26T01:03:48.320677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.24598","created_at":"2026-05-26T01:03:48.320677+00:00"},{"alias_kind":"pith_short_12","alias_value":"YBU3KTZLL3OZ","created_at":"2026-05-26T01:03:48.320677+00:00"},{"alias_kind":"pith_short_16","alias_value":"YBU3KTZLL3OZCQHK","created_at":"2026-05-26T01:03:48.320677+00:00"},{"alias_kind":"pith_short_8","alias_value":"YBU3KTZL","created_at":"2026-05-26T01:03:48.320677+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/YBU3KTZLL3OZCQHKW5W3QLOMPH","json":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH.json","graph_json":"https://pith.science/api/pith-number/YBU3KTZLL3OZCQHKW5W3QLOMPH/graph.json","events_json":"https://pith.science/api/pith-number/YBU3KTZLL3OZCQHKW5W3QLOMPH/events.json","paper":"https://pith.science/paper/YBU3KTZL"},"agent_actions":{"view_html":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH","download_json":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH.json","view_paper":"https://pith.science/paper/YBU3KTZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.24598&json=true","fetch_graph":"https://pith.science/api/pith-number/YBU3KTZLL3OZCQHKW5W3QLOMPH/graph.json","fetch_events":"https://pith.science/api/pith-number/YBU3KTZLL3OZCQHKW5W3QLOMPH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH/action/storage_attestation","attest_author":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH/action/author_attestation","sign_citation":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH/action/citation_signature","submit_replication":"https://pith.science/pith/YBU3KTZLL3OZCQHKW5W3QLOMPH/action/replication_record"}},"created_at":"2026-05-26T01:03:48.320677+00:00","updated_at":"2026-05-26T01:03:48.320677+00:00"}