{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V5LIG6OZF5PER336NLLXVNRM3S","short_pith_number":"pith:V5LIG6OZ","schema_version":"1.0","canonical_sha256":"af568379d92f5e48ef7e6ad77ab62cdca2dbc4dc0147d965637b81954cb16714","source":{"kind":"arxiv","id":"2605.13880","version":1},"attestation_state":"computed","paper":{"title":"PREPING: Building Agent Memory without Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Agents can construct competitive procedural memory for new environments using only self-generated synthetic tasks before any real experience.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jinheon Baek, Minki Kang, Sangwoo Park, Sung Ju Hwang, Yumin Choi","submitted_at":"2026-05-11T04:34:43Z","abstract_excerpt":"Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without any task-specific experience available. In this paper, we study pre-task memory construction: whether an agent can build procedural memory before observing any target-environment tasks, using only self-generated synthetic practice. Yet, synthetic interaction alone is insufficient, as without controlling what to practice and what to store, synthetic "},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13880","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T04:34:43Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"f33fac511cef95d8d740b902d062a69cd90aca34d371ab437bb74f51cd762dea","abstract_canon_sha256":"cff4abde4570b51cd1946a9a209b315530b2fe54f925b569f88b961b7b457649"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:19.198215Z","signature_b64":"oHgD6sYlvFwe/H32cLb1UMfbazvp7HScGMnXnfVG53ciFECcJalsIhQm7jX0teSNuxU1AKTWFIjgulFhfHtUDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af568379d92f5e48ef7e6ad77ab62cdca2dbc4dc0147d965637b81954cb16714","last_reissued_at":"2026-05-17T23:39:19.197500Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:19.197500Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PREPING: Building Agent Memory without Tasks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Agents can construct competitive procedural memory for new environments using only self-generated synthetic tasks before any real experience.","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Jinheon Baek, Minki Kang, Sangwoo Park, Sung Ju Hwang, Yumin Choi","submitted_at":"2026-05-11T04:34:43Z","abstract_excerpt":"Agent memory is typically constructed either offline from curated demonstrations or online from post-deployment interactions. However, regardless of how it is built, an agent faces a cold-start gap when first introduced to a new environment without any task-specific experience available. In this paper, we study pre-task memory construction: whether an agent can build procedural memory before observing any target-environment tasks, using only self-generated synthetic practice. Yet, synthetic interaction alone is insufficient, as without controlling what to practice and what to store, synthetic "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Preping substantially improves over a no-memory baseline and achieves performance competitive with strong playbook-based methods built from offline or online experience, with deployment cost $2.99× lower on AppWorld and $2.23× lower on BFCL v3 than online memory construction.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That synthetic tasks generated and filtered by the proposer-validator loop will transfer to real target-environment tasks without any direct experience of those tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Preping builds agent memory via proposer-guided synthetic practice and selective validation, matching offline/online methods at 2-3x lower deployment cost.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Agents can construct competitive procedural memory for new environments using only self-generated synthetic tasks before any real experience.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"6d51bf3eb1a40f87addfa0a6437e69e7717fa2c8358465e2b5b4b19fce4c94d6"},"source":{"id":"2605.13880","kind":"arxiv","version":1},"verdict":{"id":"11a37770-dc45-4a86-9c31-d818ca02939b","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T06:10:55.020382Z","strongest_claim":"Preping substantially improves over a no-memory baseline and achieves performance competitive with strong playbook-based methods built from offline or online experience, with deployment cost $2.99× lower on AppWorld and $2.23× lower on BFCL v3 than online memory construction.","one_line_summary":"Preping builds agent memory via proposer-guided synthetic practice and selective validation, matching offline/online methods at 2-3x lower deployment cost.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That synthetic tasks generated and filtered by the proposer-validator loop will transfer to real target-environment tasks without any direct experience of those tasks.","pith_extraction_headline":"Agents can construct competitive procedural memory for new environments using only self-generated synthetic tasks before any real experience."},"references":{"count":53,"sample":[{"doi":"10.48550/arxiv.2602.21320","year":2026,"title":"Tool-r0: Self-evolving llm agents for tool-learning from zero data","work_id":"682365bd-b781-4d4c-a78a-a0351adbdc31","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Introducing the model context protocol, November 2024","work_id":"f0cdfef8-384f-4258-b107-3db84142d5ca","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"DeepSeek-V3.2: Pushing the frontier of open large language models, 2025","work_id":"812ba0f2-05ea-49f6-a758-c2ae6d0fc49f","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.48550/arxiv.2510.04851","year":2025,"title":"LEGOMem: Modular Procedural Memory for Multi-agent LLM Systems for Workflow Automation","work_id":"81b5a1e3-7f36-4854-a305-10e386c1b07f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"10.48550/arxiv.2508.05004","year":2025,"title":"R-Zero: Self-Evolving Reasoning LLM from Zero Data","work_id":"45b39aae-1151-4087-9b48-dd16313e6306","ref_index":5,"cited_arxiv_id":"2508.05004","is_internal_anchor":true}],"resolved_work":53,"snapshot_sha256":"320ef9a362b9f83b5cba69ff837dea30c9ab8274d36be88aa5764a1597a07c53","internal_anchors":7},"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":"2605.13880","created_at":"2026-05-17T23:39:19.197621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13880v1","created_at":"2026-05-17T23:39:19.197621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13880","created_at":"2026-05-17T23:39:19.197621+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5LIG6OZF5PE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5LIG6OZF5PER336","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5LIG6OZ","created_at":"2026-05-18T12:33:37.589309+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/V5LIG6OZF5PER336NLLXVNRM3S","json":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S.json","graph_json":"https://pith.science/api/pith-number/V5LIG6OZF5PER336NLLXVNRM3S/graph.json","events_json":"https://pith.science/api/pith-number/V5LIG6OZF5PER336NLLXVNRM3S/events.json","paper":"https://pith.science/paper/V5LIG6OZ"},"agent_actions":{"view_html":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S","download_json":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S.json","view_paper":"https://pith.science/paper/V5LIG6OZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13880&json=true","fetch_graph":"https://pith.science/api/pith-number/V5LIG6OZF5PER336NLLXVNRM3S/graph.json","fetch_events":"https://pith.science/api/pith-number/V5LIG6OZF5PER336NLLXVNRM3S/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S/action/storage_attestation","attest_author":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S/action/author_attestation","sign_citation":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S/action/citation_signature","submit_replication":"https://pith.science/pith/V5LIG6OZF5PER336NLLXVNRM3S/action/replication_record"}},"created_at":"2026-05-17T23:39:19.197621+00:00","updated_at":"2026-05-17T23:39:19.197621+00:00"}