{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:QO7SHORTWYYHW37DPA2UGZ725V","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":"14b4efe2dffb8897b15f584f54a0bfed416da8e06ad60eb4df394c153bfbf759","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T05:53:09Z","title_canon_sha256":"3283edd01acd56799f9854b6b46937136a436ef5d9896d89ea6be650f071a43e"},"schema_version":"1.0","source":{"id":"2505.03209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.03209","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.03209v1","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.03209","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"pith_short_12","alias_value":"QO7SHORTWYYH","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"pith_short_16","alias_value":"QO7SHORTWYYHW37D","created_at":"2026-07-05T10:59:12Z"},{"alias_kind":"pith_short_8","alias_value":"QO7SHORT","created_at":"2026-07-05T10:59:12Z"}],"graph_snapshots":[{"event_id":"sha256:6be79d9a383cb93c69b6ded55a24cd1722e700cafed20a0dd62b45188079daf0","target":"graph","created_at":"2026-07-05T10:59:12Z","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/2505.03209/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning from expert demonstrations has long remained a challenging research problem, and existing state-of-the-art methods using behavioral cloning plus further RL training often suffer from poor generalization, low sample efficiency, and poor model interpretability. Inspired by the strong reasoning abilities of large language models (LLMs), we propose a novel strategy-based reinforcement learning framework integrated with LLMs called DYnamic STrategy Induction with Llms for reinforcement learning (DYSTIL) to overcome these limitations. DYSTIL dynamically queries a strategy-gene","authors_text":"Borui Wang, Kathleen McKeown, Rex Ying","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T05:53:09Z","title":"DYSTIL: Dynamic Strategy Induction with Large Language Models for Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.03209","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":"sha256:0fbb72f953d2473c0c18e51a74aed33114ddbdf07b95057917ffddc8486aff9a","target":"record","created_at":"2026-07-05T10:59:12Z","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":"14b4efe2dffb8897b15f584f54a0bfed416da8e06ad60eb4df394c153bfbf759","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-06T05:53:09Z","title_canon_sha256":"3283edd01acd56799f9854b6b46937136a436ef5d9896d89ea6be650f071a43e"},"schema_version":"1.0","source":{"id":"2505.03209","kind":"arxiv","version":1}},"canonical_sha256":"83bf23ba33b6307b6fe378354367faed7440f28bb0ad6ad04a1603fb4d3dbf5d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83bf23ba33b6307b6fe378354367faed7440f28bb0ad6ad04a1603fb4d3dbf5d","first_computed_at":"2026-07-05T10:59:12.194740Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:59:12.194740Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8dycAsDZ65pWd9J5lmDi2jCcDcOq7TF9s4iM6xoisVlG9bb5GnvlRw/x9pnzYBownEOevlOS8EqQQaQaYvDwBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:59:12.195214Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.03209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0fbb72f953d2473c0c18e51a74aed33114ddbdf07b95057917ffddc8486aff9a","sha256:6be79d9a383cb93c69b6ded55a24cd1722e700cafed20a0dd62b45188079daf0"],"state_sha256":"c6faade1950a748719e1c9e889eb20425b18c09459ff4574c48558392618ec28"}