{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SNKKA5T4TNXHDKLQP3XABL4LMX","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":"b6186464397dd9eb2139da44255d721c751103104e0d61c7ab1c470fe898097b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T14:53:19Z","title_canon_sha256":"05a323aa685828d4d60f932bb5ca9d2b7e68cb93dcb771e207174805747acf0e"},"schema_version":"1.0","source":{"id":"2606.08656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.08656","created_at":"2026-06-09T01:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2606.08656v1","created_at":"2026-06-09T01:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.08656","created_at":"2026-06-09T01:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"SNKKA5T4TNXH","created_at":"2026-06-09T01:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"SNKKA5T4TNXHDKLQ","created_at":"2026-06-09T01:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"SNKKA5T4","created_at":"2026-06-09T01:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:a783be160e8609fc3da3e0e34b9421c75539ebb71c7aea7d3cdccb3fe1600205","target":"graph","created_at":"2026-06-09T01:05:42Z","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/2606.08656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model (LLM) agents are increasingly deployed in long-running settings where improving through experience at test time becomes important. A common approach is to update an explicit memory after each interaction to guide future decisions. However, most existing methods rely on hand-designed prompting rules, making it difficult to align memory updates with downstream objectives over multi-step horizons consistently. We propose MemoPilot, a plug-in memory copilot that explicitly trains the memory update process to improve a frozen LLM's performance across sequential interactions. We","authors_text":"Aohan Zeng, Can Huang, Jie Tang, Jinhua Du, Wenhan Ma, Wenxuan Huang, Xingyu Guo, Xuancheng Huang, Xu Sun, Yishuo Cai, Yuyang Hu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T14:53:19Z","title":"From Player to Master: Enhancing Test-Time Learning of LLM Agents via Reinforcement Learning over Memory"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.08656","kind":"arxiv","version":1},"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":"sha256:0fd14c7498e84d04bd6eb177bbeab8a39abf0e671ee7bb5ead893792a73f888f","target":"record","created_at":"2026-06-09T01:05:42Z","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":"b6186464397dd9eb2139da44255d721c751103104e0d61c7ab1c470fe898097b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-07T14:53:19Z","title_canon_sha256":"05a323aa685828d4d60f932bb5ca9d2b7e68cb93dcb771e207174805747acf0e"},"schema_version":"1.0","source":{"id":"2606.08656","kind":"arxiv","version":1}},"canonical_sha256":"9354a0767c9b6e71a9707eee00af8b65ffb106a6254042cf70658e326c1939a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9354a0767c9b6e71a9707eee00af8b65ffb106a6254042cf70658e326c1939a1","first_computed_at":"2026-06-09T01:05:42.953860Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:05:42.953860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JpEVIfndgfnAsteFFHeBhpXRGWn1hGtazCyB/DIQPAs84dDpRau0KkZ9M9sbaOC3hKrjY/qNPzwglqbg1bXKBQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:05:42.954274Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.08656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fd14c7498e84d04bd6eb177bbeab8a39abf0e671ee7bb5ead893792a73f888f","sha256:a783be160e8609fc3da3e0e34b9421c75539ebb71c7aea7d3cdccb3fe1600205"],"state_sha256":"f6bc5f2fac7f5f31a6a74b1581bae833c5b71daa8dd01de20e40b57d87a4f51b"}