{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IIWQVRGSCHTFFJH6MEUAW44REB","short_pith_number":"pith:IIWQVRGS","schema_version":"1.0","canonical_sha256":"422d0ac4d211e652a4fe61280b73912069bd5ab98e7f0cb0d8b7c57ddb94a974","source":{"kind":"arxiv","id":"2606.29824","version":1},"attestation_state":"computed","paper":{"title":"Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengfeng Zhao, Jun Zhao, Kang Liu, Shizhu He, Yequan Wang, Yuqiao Tan","submitted_at":"2026-06-29T06:05:25Z","abstract_excerpt":"While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interaction, yet current agents lack the necessary persistent procedural memory. Existing approaches predominantly employ Retrieval-Augmented Generation (RAG) to inject explicit textual guidelines into model contexts. However, relying solely on symbolic instructions can introduce a text-action disconnect, frequently failing to activate the internal representations necessary for correct task execution. To address this, the pa"},"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":"2606.29824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-29T06:05:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6100ad804e0cde478f94f593e1c5a9668e901bf9f26880302e7756b8e8982d11","abstract_canon_sha256":"87796c14588a1a8723eae641489604b9797c87b903403e5aac03e250991499ad"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:36.953554Z","signature_b64":"OmnV79J6Msxqu+tZRzOxsadqvNT8I1Mey6VPuAeFV4B/hxca/OcGUcfGWC0CETH1l2lL0GdvWG4LA/9y/anRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"422d0ac4d211e652a4fe61280b73912069bd5ab98e7f0cb0d8b7c57ddb94a974","last_reissued_at":"2026-06-30T02:17:36.952990Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:36.952990Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Procedural Memory: Empowering LLM Agents with Implicit Activation Steering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengfeng Zhao, Jun Zhao, Kang Liu, Shizhu He, Yequan Wang, Yuqiao Tan","submitted_at":"2026-06-29T06:05:25Z","abstract_excerpt":"While Large Language Models (LLMs) excel as static solvers, transforming them into autonomous agents remains challenging. This transition requires continuous environmental interaction, yet current agents lack the necessary persistent procedural memory. Existing approaches predominantly employ Retrieval-Augmented Generation (RAG) to inject explicit textual guidelines into model contexts. However, relying solely on symbolic instructions can introduce a text-action disconnect, frequently failing to activate the internal representations necessary for correct task execution. To address this, the pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29824","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/2606.29824/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":"2606.29824","created_at":"2026-06-30T02:17:36.953082+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29824v1","created_at":"2026-06-30T02:17:36.953082+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29824","created_at":"2026-06-30T02:17:36.953082+00:00"},{"alias_kind":"pith_short_12","alias_value":"IIWQVRGSCHTF","created_at":"2026-06-30T02:17:36.953082+00:00"},{"alias_kind":"pith_short_16","alias_value":"IIWQVRGSCHTFFJH6","created_at":"2026-06-30T02:17:36.953082+00:00"},{"alias_kind":"pith_short_8","alias_value":"IIWQVRGS","created_at":"2026-06-30T02:17:36.953082+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/IIWQVRGSCHTFFJH6MEUAW44REB","json":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB.json","graph_json":"https://pith.science/api/pith-number/IIWQVRGSCHTFFJH6MEUAW44REB/graph.json","events_json":"https://pith.science/api/pith-number/IIWQVRGSCHTFFJH6MEUAW44REB/events.json","paper":"https://pith.science/paper/IIWQVRGS"},"agent_actions":{"view_html":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB","download_json":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB.json","view_paper":"https://pith.science/paper/IIWQVRGS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29824&json=true","fetch_graph":"https://pith.science/api/pith-number/IIWQVRGSCHTFFJH6MEUAW44REB/graph.json","fetch_events":"https://pith.science/api/pith-number/IIWQVRGSCHTFFJH6MEUAW44REB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB/action/storage_attestation","attest_author":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB/action/author_attestation","sign_citation":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB/action/citation_signature","submit_replication":"https://pith.science/pith/IIWQVRGSCHTFFJH6MEUAW44REB/action/replication_record"}},"created_at":"2026-06-30T02:17:36.953082+00:00","updated_at":"2026-06-30T02:17:36.953082+00:00"}