{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IRIJPBSPQXNEQSC2VKK5IRDBHY","short_pith_number":"pith:IRIJPBSP","schema_version":"1.0","canonical_sha256":"445097864f85da48485aaa95d444613e13bf07aae01ff77977d9c6e9487ded3f","source":{"kind":"arxiv","id":"2605.21463","version":1},"attestation_state":"computed","paper":{"title":"Mem-$\\pi$: Adaptive Memory through Learning When and What to Generate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre Lacoste, Bang Liu, Chao Wang, Christopher Pal, Hadi Nekoei, Perouz Taslakian, Spandana Gella, Xiaoqiang Wang","submitted_at":"2026-05-20T17:51:05Z","abstract_excerpt":"We present Mem-$\\pi$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on similarity-based retrieval from episodic memory banks or skill libraries, returning static entries that often misalign with the current context. In contrast, Mem-$\\pi$ uses a dedicated language or vision-language model with its own parameters, separate from the downstream agent, to generate context-specific guidance for complex tasks. Conditioned on the curre"},"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":"2605.21463","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-20T17:51:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b9c03bbc2f5b2b79ce43b6307363ae3ab977b279a5d762424b890dee05e1bd11","abstract_canon_sha256":"4efa3eedb85adf57fc36d99d810cd9a8a3bf503581e296b049f9dd2ffb49ac82"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:38.452614Z","signature_b64":"oXNoplceAsgov28lHJt+mF+B7HGlI/9gOwaPkxFqOFkR18WXyVqzuk8C9nbe5GU8SmuwdncSWAXroS0JYyQwCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"445097864f85da48485aaa95d444613e13bf07aae01ff77977d9c6e9487ded3f","last_reissued_at":"2026-05-21T02:05:38.451994Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:38.451994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mem-$\\pi$: Adaptive Memory through Learning When and What to Generate","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Alexandre Lacoste, Bang Liu, Chao Wang, Christopher Pal, Hadi Nekoei, Perouz Taslakian, Spandana Gella, Xiaoqiang Wang","submitted_at":"2026-05-20T17:51:05Z","abstract_excerpt":"We present Mem-$\\pi$, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from external memory stores. Existing memory-augmented agents typically rely on similarity-based retrieval from episodic memory banks or skill libraries, returning static entries that often misalign with the current context. In contrast, Mem-$\\pi$ uses a dedicated language or vision-language model with its own parameters, separate from the downstream agent, to generate context-specific guidance for complex tasks. Conditioned on the curre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21463","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/2605.21463/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":"2605.21463","created_at":"2026-05-21T02:05:38.452112+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21463v1","created_at":"2026-05-21T02:05:38.452112+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21463","created_at":"2026-05-21T02:05:38.452112+00:00"},{"alias_kind":"pith_short_12","alias_value":"IRIJPBSPQXNE","created_at":"2026-05-21T02:05:38.452112+00:00"},{"alias_kind":"pith_short_16","alias_value":"IRIJPBSPQXNEQSC2","created_at":"2026-05-21T02:05:38.452112+00:00"},{"alias_kind":"pith_short_8","alias_value":"IRIJPBSP","created_at":"2026-05-21T02:05:38.452112+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/IRIJPBSPQXNEQSC2VKK5IRDBHY","json":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY.json","graph_json":"https://pith.science/api/pith-number/IRIJPBSPQXNEQSC2VKK5IRDBHY/graph.json","events_json":"https://pith.science/api/pith-number/IRIJPBSPQXNEQSC2VKK5IRDBHY/events.json","paper":"https://pith.science/paper/IRIJPBSP"},"agent_actions":{"view_html":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY","download_json":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY.json","view_paper":"https://pith.science/paper/IRIJPBSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21463&json=true","fetch_graph":"https://pith.science/api/pith-number/IRIJPBSPQXNEQSC2VKK5IRDBHY/graph.json","fetch_events":"https://pith.science/api/pith-number/IRIJPBSPQXNEQSC2VKK5IRDBHY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY/action/storage_attestation","attest_author":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY/action/author_attestation","sign_citation":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY/action/citation_signature","submit_replication":"https://pith.science/pith/IRIJPBSPQXNEQSC2VKK5IRDBHY/action/replication_record"}},"created_at":"2026-05-21T02:05:38.452112+00:00","updated_at":"2026-05-21T02:05:38.452112+00:00"}