{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZI6DO73A5MIBC7ODY7W4YPBIB2","short_pith_number":"pith:ZI6DO73A","schema_version":"1.0","canonical_sha256":"ca3c377f60eb10117dc3c7edcc3c280e827556477a81a7bbd819237f0e4465f8","source":{"kind":"arxiv","id":"2306.03604","version":8},"attestation_state":"computed","paper":{"title":"Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Hu, Bin Liu, Chenyang Zhao, Pu Zhang, Yuanhang Yang, Zenglin Xu, Zihao Zhou","submitted_at":"2023-06-06T11:49:09Z","abstract_excerpt":"Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. Recent studies have demonstrated that LLMs can assist an embodied agent in solving complex sequential decision making tasks by providing high-level instructions. However, interactions with LLMs can be time-consuming. In many practical scenarios, it requires a significant amount of storage space that can only be deployed on remote cloud servers. Additionally, using commercial LLMs can be costly since they may charge based on usage frequency. In this paper, we explore how to enable intellige"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2306.03604","kind":"arxiv","version":8},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-06T11:49:09Z","cross_cats_sorted":[],"title_canon_sha256":"50451388bf40264784ab9bb13fd0a21d864a07b399c28e0f29364ad5e4612d69","abstract_canon_sha256":"dd2b8121a01444bea503ff7e1437256b41681c1cd6b10ddf1f19d9439e00872b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:42.334066Z","signature_b64":"9h3rjV1eW4+1obu8LbhcHosh18fxsLhig6TwOy99bTzjkP09KfyK405oEPXSRHMUjCbLUoYNthbiUhNheUJGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca3c377f60eb10117dc3c7edcc3c280e827556477a81a7bbd819237f0e4465f8","last_reissued_at":"2026-07-05T08:36:42.333601Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:42.333601Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bin Hu, Bin Liu, Chenyang Zhao, Pu Zhang, Yuanhang Yang, Zenglin Xu, Zihao Zhou","submitted_at":"2023-06-06T11:49:09Z","abstract_excerpt":"Large language models (LLMs) encode a vast amount of world knowledge acquired from massive text datasets. Recent studies have demonstrated that LLMs can assist an embodied agent in solving complex sequential decision making tasks by providing high-level instructions. However, interactions with LLMs can be time-consuming. In many practical scenarios, it requires a significant amount of storage space that can only be deployed on remote cloud servers. Additionally, using commercial LLMs can be costly since they may charge based on usage frequency. In this paper, we explore how to enable intellige"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.03604","kind":"arxiv","version":8},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2306.03604/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2306.03604","created_at":"2026-07-05T08:36:42.333659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.03604v8","created_at":"2026-07-05T08:36:42.333659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.03604","created_at":"2026-07-05T08:36:42.333659+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZI6DO73A5MIB","created_at":"2026-07-05T08:36:42.333659+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZI6DO73A5MIBC7OD","created_at":"2026-07-05T08:36:42.333659+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZI6DO73A","created_at":"2026-07-05T08:36:42.333659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2310.07099","citing_title":"ClausewitzGPT Framework: A New Frontier in Theoretical Large Language Model Enhanced Information Operations","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":132,"is_internal_anchor":false},{"citing_arxiv_id":"2310.03714","citing_title":"DSPy: Compiling Declarative Language Model Calls into Self-Improving Pipelines","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07462","citing_title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","ref_index":22,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2","json":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2.json","graph_json":"https://pith.science/api/pith-number/ZI6DO73A5MIBC7ODY7W4YPBIB2/graph.json","events_json":"https://pith.science/api/pith-number/ZI6DO73A5MIBC7ODY7W4YPBIB2/events.json","paper":"https://pith.science/paper/ZI6DO73A"},"agent_actions":{"view_html":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2","download_json":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2.json","view_paper":"https://pith.science/paper/ZI6DO73A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.03604&json=true","fetch_graph":"https://pith.science/api/pith-number/ZI6DO73A5MIBC7ODY7W4YPBIB2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZI6DO73A5MIBC7ODY7W4YPBIB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2/action/storage_attestation","attest_author":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2/action/author_attestation","sign_citation":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2/action/citation_signature","submit_replication":"https://pith.science/pith/ZI6DO73A5MIBC7ODY7W4YPBIB2/action/replication_record"}},"created_at":"2026-07-05T08:36:42.333659+00:00","updated_at":"2026-07-05T08:36:42.333659+00:00"}