{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Q3QNSGNRRDFZALMY7D4D56CMYO","short_pith_number":"pith:Q3QNSGNR","schema_version":"1.0","canonical_sha256":"86e0d919b188cb902d98f8f83ef84cc396ef724a467e4670c019740665391657","source":{"kind":"arxiv","id":"2305.11598","version":1},"attestation_state":"computed","paper":{"title":"Introspective Tips: Large Language Model for In-Context Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dongmei Zhang, Fangkai Yang, Hang Dong, Jie Yan, Liting Chen, Lu Wang, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Shuang Li, Si Qin, Yali Du","submitted_at":"2023-05-19T11:20:37Z","abstract_excerpt":"The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips\" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and gene"},"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":"2305.11598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2023-05-19T11:20:37Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"34d2f1cd84bdbefcd171a50ec8295f62b28d9d757b65f569aa727be4062f6567","abstract_canon_sha256":"8938e23208a489787737947b883988cfed7eb38c294d80d4f208264a8ca657a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:11:49.048152Z","signature_b64":"DgscC+D9gN6Ow0LsZHtDr/jNXiY8UH1cDrz1tJASbXjvZx1F6JQtfdnLyJ66lrAjRKNi1s5bOiRjKau/wWgWAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86e0d919b188cb902d98f8f83ef84cc396ef724a467e4670c019740665391657","last_reissued_at":"2026-07-05T06:11:49.047743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:11:49.047743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Introspective Tips: Large Language Model for In-Context Decision Making","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Dongmei Zhang, Fangkai Yang, Hang Dong, Jie Yan, Liting Chen, Lu Wang, Pu Zhao, Qingwei Lin, Saravan Rajmohan, Shuang Li, Si Qin, Yali Du","submitted_at":"2023-05-19T11:20:37Z","abstract_excerpt":"The emergence of large language models (LLMs) has substantially influenced natural language processing, demonstrating exceptional results across various tasks. In this study, we employ ``Introspective Tips\" to facilitate LLMs in self-optimizing their decision-making. By introspectively examining trajectories, LLM refines its policy by generating succinct and valuable tips. Our method enhances the agent's performance in both few-shot and zero-shot learning situations by considering three essential scenarios: learning from the agent's past experiences, integrating expert demonstrations, and gene"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11598","kind":"arxiv","version":1},"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/2305.11598/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":"2305.11598","created_at":"2026-07-05T06:11:49.047799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.11598v1","created_at":"2026-07-05T06:11:49.047799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11598","created_at":"2026-07-05T06:11:49.047799+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3QNSGNRRDFZ","created_at":"2026-07-05T06:11:49.047799+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3QNSGNRRDFZALMY","created_at":"2026-07-05T06:11:49.047799+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3QNSGNR","created_at":"2026-07-05T06:11:49.047799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07603","citing_title":"MetaEvo: A Meta-Optimization Framework for Experience-Driven Agent Evolution","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16079","citing_title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16079","citing_title":"EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":84,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO","json":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO.json","graph_json":"https://pith.science/api/pith-number/Q3QNSGNRRDFZALMY7D4D56CMYO/graph.json","events_json":"https://pith.science/api/pith-number/Q3QNSGNRRDFZALMY7D4D56CMYO/events.json","paper":"https://pith.science/paper/Q3QNSGNR"},"agent_actions":{"view_html":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO","download_json":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO.json","view_paper":"https://pith.science/paper/Q3QNSGNR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.11598&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3QNSGNRRDFZALMY7D4D56CMYO/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3QNSGNRRDFZALMY7D4D56CMYO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO/action/storage_attestation","attest_author":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO/action/author_attestation","sign_citation":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO/action/citation_signature","submit_replication":"https://pith.science/pith/Q3QNSGNRRDFZALMY7D4D56CMYO/action/replication_record"}},"created_at":"2026-07-05T06:11:49.047799+00:00","updated_at":"2026-07-05T06:11:49.047799+00:00"}