{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DEGV7IIVFYXYPULUVA2JKZESY3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"79d6fdce703f78a9085265420514cff74f9514907c031115fe0c7cd703c242c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","title_canon_sha256":"e9d7ddadf31ed47c536d491f78a13b58489d1e1a9cabd5e0b029bfa2630684c7"},"schema_version":"1.0","source":{"id":"2601.18510","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2601.18510","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"arxiv_version","alias_value":"2601.18510v2","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.18510","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_12","alias_value":"DEGV7IIVFYXY","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_16","alias_value":"DEGV7IIVFYXYPULU","created_at":"2026-06-08T01:03:56Z"},{"alias_kind":"pith_short_8","alias_value":"DEGV7IIV","created_at":"2026-06-08T01:03:56Z"}],"graph_snapshots":[{"event_id":"sha256:400568541034fd2c8d14d8cde0e10615bd85e8ae07088e9ef55eeb6842223088","target":"graph","created_at":"2026-06-08T01:03:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2601.18510/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Large Language Model (LLM) agents excel at general tasks, they inherently struggle with continual adaptation due to the frozen weights after deployment. Conventional reinforcement learning (RL) offers a solution but incurs prohibitive computational costs and the risk of catastrophic forgetting. We introduce Just-In-Time Reinforcement Learning (JitRL), a training-free framework that enables test-time policy optimization without any gradient updates. JitRL maintains a dynamic, non-parametric memory of experiences and retrieves relevant trajectories to estimate action advantages on-the-fly.","authors_text":"Ailin Deng, Bryan Hooi, Shuo Ji, Tri Cao, Xuan Zhang, Yibo Li, Yufei He, Zijie Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","title":"Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.18510","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:110478d12d4b956fa7208753eab6f6b87be98e712528b4e776f0bbdfcc92e7ae","target":"record","created_at":"2026-06-08T01:03:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"79d6fdce703f78a9085265420514cff74f9514907c031115fe0c7cd703c242c9","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-01-26T14:16:51Z","title_canon_sha256":"e9d7ddadf31ed47c536d491f78a13b58489d1e1a9cabd5e0b029bfa2630684c7"},"schema_version":"1.0","source":{"id":"2601.18510","kind":"arxiv","version":2}},"canonical_sha256":"190d5fa1152e2f87d174a834956492c6f6b66e467199dbe0319641efc268f0dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"190d5fa1152e2f87d174a834956492c6f6b66e467199dbe0319641efc268f0dd","first_computed_at":"2026-06-08T01:03:56.377023Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:03:56.377023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3iKhF/u159mAsFKxg0EQ0gHCRsqvt6Wn7xkX9EVjp+dF+OiQcItB6D1VVkZ1L2DP7R2aoJSnSCW9RfX4iX9oAw==","signature_status":"signed_v1","signed_at":"2026-06-08T01:03:56.377999Z","signed_message":"canonical_sha256_bytes"},"source_id":"2601.18510","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:110478d12d4b956fa7208753eab6f6b87be98e712528b4e776f0bbdfcc92e7ae","sha256:400568541034fd2c8d14d8cde0e10615bd85e8ae07088e9ef55eeb6842223088"],"state_sha256":"f04a52678ca8bb523bd3f7538a2fc25ab996d623a397612d12341574ebfd0e63"}