{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:VKMYIA77HH2PTV4XLMJAYCKGHL","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":"f5989caadbdea56f8dbc5be636def971c20d90226064963078eb637cecec365c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-29T12:16:08Z","title_canon_sha256":"92a1b388e96cd4c5aa969d66134f6c33b0d75dc2ecc29bfa5a992f01c6320a7b"},"schema_version":"1.0","source":{"id":"2404.18638","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18638","created_at":"2026-07-05T08:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18638v1","created_at":"2026-07-05T08:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18638","created_at":"2026-07-05T08:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"VKMYIA77HH2P","created_at":"2026-07-05T08:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"VKMYIA77HH2PTV4X","created_at":"2026-07-05T08:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"VKMYIA77","created_at":"2026-07-05T08:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:fa7dc63506030f92dc77f4fa3cb09ab6d9236f66e54ad69781f2eaceaa79675e","target":"graph","created_at":"2026-07-05T08:13:18Z","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/2404.18638/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) encapsulate an extensive amount of world knowledge, and this has enabled their application in various domains to improve the performance of a variety of Natural Language Processing (NLP) tasks. This has also facilitated a more accessible paradigm of conversation-based interactions between humans and AI systems to solve intended problems. However, one interesting avenue that shows untapped potential is the use of LLMs as Reinforcement Learning (RL) agents to enable conversational RL problem solving. Therefore, in this study, we explore the concept of formulating Mar","authors_text":"Domingo Huh, Sina Gholamian","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-29T12:16:08Z","title":"Reinforcement Learning Problem Solving with Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18638","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":"sha256:4db8504b6eb503081ce0fcc36dbe4d11e21690ec7d8d677fbbc54984da4a3939","target":"record","created_at":"2026-07-05T08:13:18Z","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":"f5989caadbdea56f8dbc5be636def971c20d90226064963078eb637cecec365c","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-29T12:16:08Z","title_canon_sha256":"92a1b388e96cd4c5aa969d66134f6c33b0d75dc2ecc29bfa5a992f01c6320a7b"},"schema_version":"1.0","source":{"id":"2404.18638","kind":"arxiv","version":1}},"canonical_sha256":"aa998403ff39f4f9d7975b120c09463acc62cd43c0c4ae4f36feb355049b5ddd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa998403ff39f4f9d7975b120c09463acc62cd43c0c4ae4f36feb355049b5ddd","first_computed_at":"2026-07-05T08:13:18.678686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:18.678686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GekiX/HKD0R9+r1GN3qKUb5eJUAAaIgrHX7af+uqdATZ8WV17TsXUopxgtbPNr+1X5ge9YLP2XuP8u+8HCc2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:18.679098Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18638","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4db8504b6eb503081ce0fcc36dbe4d11e21690ec7d8d677fbbc54984da4a3939","sha256:fa7dc63506030f92dc77f4fa3cb09ab6d9236f66e54ad69781f2eaceaa79675e"],"state_sha256":"9ebef9a77c193cb9c5058729e5e0f67acdb449ec0e01e52ca141c6e8af7cb7cb"}