{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MJNLBHKNIQZAS4LHX3DLU6OO3E","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":"7c4c29552d2761c7a62d3ebc90ce5509d08ca58863f58fbc0b06ad90526807e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:29:27Z","title_canon_sha256":"8c5f63ba2fec572c0cd721197dc207c85ec81fba86080e874b0144dbdaba38b5"},"schema_version":"1.0","source":{"id":"2605.21240","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.21240","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"arxiv_version","alias_value":"2605.21240v1","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21240","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"pith_short_12","alias_value":"MJNLBHKNIQZA","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"pith_short_16","alias_value":"MJNLBHKNIQZAS4LH","created_at":"2026-05-21T01:05:45Z"},{"alias_kind":"pith_short_8","alias_value":"MJNLBHKN","created_at":"2026-05-21T01:05:45Z"}],"graph_snapshots":[{"event_id":"sha256:ab89d9e216170976aee3a8db76e385ef8c12775af974723305ec2b18b929ccf8","target":"graph","created_at":"2026-05-21T01:05:45Z","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/2605.21240/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents cannot learn on the fly at test time. Self-evolving agents address this by accumulating memory and reflection across episodes rather than requiring model-weight updates. However, these agents often suffer from exploration collapse: as memory grows, behavior concentrates around familiar high-reward routines, reducing the chance of discovering better alternatives. To address this problem, we propose Autonomous Policy EXplora","authors_text":"Bryan Hooi, Jiashuo Yang, Shizun Wang, Yibo Li, Yuan Sui, Yufei He, Zhiyuan Hu, Zhi Zheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:29:27Z","title":"APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21240","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":"sha256:33f64c12679ca8455b3cc14d52bc7f37d1d704c251d69496a67007ea75b3138f","target":"record","created_at":"2026-05-21T01:05:45Z","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":"7c4c29552d2761c7a62d3ebc90ce5509d08ca58863f58fbc0b06ad90526807e5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T14:29:27Z","title_canon_sha256":"8c5f63ba2fec572c0cd721197dc207c85ec81fba86080e874b0144dbdaba38b5"},"schema_version":"1.0","source":{"id":"2605.21240","kind":"arxiv","version":1}},"canonical_sha256":"625ab09d4d4432097167bec6ba79ced923466ffde4074b16a48744367545bf1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"625ab09d4d4432097167bec6ba79ced923466ffde4074b16a48744367545bf1b","first_computed_at":"2026-05-21T01:05:45.307350Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:05:45.307350Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r6DqxPaycXJLJDgs+AFD7wKwKpEh155hafz43HD6gfKOJ6qxKplzgZEmxbAs+dDDGO4ubv+16hC3/NcfSCKIDA==","signature_status":"signed_v1","signed_at":"2026-05-21T01:05:45.307929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.21240","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:33f64c12679ca8455b3cc14d52bc7f37d1d704c251d69496a67007ea75b3138f","sha256:ab89d9e216170976aee3a8db76e385ef8c12775af974723305ec2b18b929ccf8"],"state_sha256":"1df2e003b27722622bf08a9ab320ea0f240226140ef325c6c7a7200be564e850"}