{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AGHHOCHFOECEACDMOLYR4QAWZN","short_pith_number":"pith:AGHHOCHF","schema_version":"1.0","canonical_sha256":"018e7708e5710440086c72f11e4016cb59354b09caf94cec1cdb96fb06089512","source":{"kind":"arxiv","id":"2602.06025","version":2},"attestation_state":"computed","paper":{"title":"Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Chengwei Qin, Haodong Yue, Haozhen Zhang, Jianzhu Bao, Jiaxuan You, Quanyu Long, Tao Feng, Weizhi Zhang, Wenya Wang, Xiao Li","submitted_at":"2026-02-05T18:57:09Z","abstract_excerpt":"Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic memory construction that can be inefficient and may discard query-critical information. Although runtime memory utilization is a natural alternative, prior work often incurs substantial overhead and offers limited explicit control over the performance-cost trade-off. In this work, we present \\textbf{BudgetMem}, a runtime agent memory framework for explicit, query-aware performance-cost control. BudgetMem structures memory proces"},"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":"2602.06025","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-05T18:57:09Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"9fca933967de0c48ae251a12635fe6b94f72e906670cd006fff7953969fc15d6","abstract_canon_sha256":"e0a82016d829ac52e8bd5502e072f4f9161ff4e0e44625c940db6d247363372b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:15.963808Z","signature_b64":"1WGEgkMLdFK1g6GxVymc++q25c6ktqHXoJ6cFq1o2A8+bS5sNQcqh0p3VZD4ng6KQItpZksevGz2T3GCG2ksBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"018e7708e5710440086c72f11e4016cb59354b09caf94cec1cdb96fb06089512","last_reissued_at":"2026-05-21T01:05:15.963004Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:15.963004Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bowen Jin, Chengwei Qin, Haodong Yue, Haozhen Zhang, Jianzhu Bao, Jiaxuan You, Quanyu Long, Tao Feng, Weizhi Zhang, Wenya Wang, Xiao Li","submitted_at":"2026-02-05T18:57:09Z","abstract_excerpt":"Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offline, query-agnostic memory construction that can be inefficient and may discard query-critical information. Although runtime memory utilization is a natural alternative, prior work often incurs substantial overhead and offers limited explicit control over the performance-cost trade-off. In this work, we present \\textbf{BudgetMem}, a runtime agent memory framework for explicit, query-aware performance-cost control. BudgetMem structures memory proces"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06025","kind":"arxiv","version":2},"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/2602.06025/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":"2602.06025","created_at":"2026-05-21T01:05:15.963116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.06025v2","created_at":"2026-05-21T01:05:15.963116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06025","created_at":"2026-05-21T01:05:15.963116+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGHHOCHFOECE","created_at":"2026-05-21T01:05:15.963116+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGHHOCHFOECEACDM","created_at":"2026-05-21T01:05:15.963116+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGHHOCHF","created_at":"2026-05-21T01:05:15.963116+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.08224","citing_title":"Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering","ref_index":186,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN","json":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN.json","graph_json":"https://pith.science/api/pith-number/AGHHOCHFOECEACDMOLYR4QAWZN/graph.json","events_json":"https://pith.science/api/pith-number/AGHHOCHFOECEACDMOLYR4QAWZN/events.json","paper":"https://pith.science/paper/AGHHOCHF"},"agent_actions":{"view_html":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN","download_json":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN.json","view_paper":"https://pith.science/paper/AGHHOCHF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.06025&json=true","fetch_graph":"https://pith.science/api/pith-number/AGHHOCHFOECEACDMOLYR4QAWZN/graph.json","fetch_events":"https://pith.science/api/pith-number/AGHHOCHFOECEACDMOLYR4QAWZN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN/action/storage_attestation","attest_author":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN/action/author_attestation","sign_citation":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN/action/citation_signature","submit_replication":"https://pith.science/pith/AGHHOCHFOECEACDMOLYR4QAWZN/action/replication_record"}},"created_at":"2026-05-21T01:05:15.963116+00:00","updated_at":"2026-05-21T01:05:15.963116+00:00"}