{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:62X4MDFD3NNTNLZHONFX5UTPOK","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":"1e459dd4629665110048f8d4fc1555c98e6d311b7b0e87e848e7f4ced3644839","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T00:48:12Z","title_canon_sha256":"bce4e11f62ea38f9a7a1878625ea49b15aefad4be8e4fd0e192bb6a852b0d78d"},"schema_version":"1.0","source":{"id":"2505.00234","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.00234","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2505.00234v3","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00234","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"62X4MDFD3NNT","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"62X4MDFD3NNTNLZH","created_at":"2026-07-05T11:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"62X4MDFD","created_at":"2026-07-05T11:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:4bebca89a15e4d844838ab230080ab07cf0cc3566bb41d807c21bb9811284ea4","target":"graph","created_at":"2026-07-05T11:04:22Z","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/2505.00234/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Improving Large Language Model (LLM) agents for sequential decision-making tasks typically requires extensive task-specific knowledge engineering--custom prompts, curated examples, and specialized observation/action spaces. We investigate a different approach where agents automatically improve by learning from their own successful experiences without human intervention. Our method constructs and refines a database of self-generated trajectories that serve as in-context examples for future tasks. Even naive accumulation of successful trajectories yields substantial performance gains across thre","authors_text":"Kayvon Fatahalian, Vishnu Sarukkai, Zhiqiang Xie","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T00:48:12Z","title":"Self-Generated In-Context Examples Improve LLM Agents for Sequential Decision-Making Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00234","kind":"arxiv","version":3},"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":"sha256:60a0dd197e11a67557e6e16f33452ef52074a02c8c34190e824ffa62f3fc27d0","target":"record","created_at":"2026-07-05T11:04:22Z","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":"1e459dd4629665110048f8d4fc1555c98e6d311b7b0e87e848e7f4ced3644839","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-01T00:48:12Z","title_canon_sha256":"bce4e11f62ea38f9a7a1878625ea49b15aefad4be8e4fd0e192bb6a852b0d78d"},"schema_version":"1.0","source":{"id":"2505.00234","kind":"arxiv","version":3}},"canonical_sha256":"f6afc60ca3db5b36af27734b7ed26f72b6f357d60d45dae8de80caba874d138a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6afc60ca3db5b36af27734b7ed26f72b6f357d60d45dae8de80caba874d138a","first_computed_at":"2026-07-05T11:04:22.059780Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:04:22.059780Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"afH35H1S8LGQP35ghKnKj5XqnzvfGZz8nWYp5Rzih14UiFHyza24OMsgGXsuwLUZs65L4KbCYeUMFJoLsNefBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:04:22.060251Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.00234","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60a0dd197e11a67557e6e16f33452ef52074a02c8c34190e824ffa62f3fc27d0","sha256:4bebca89a15e4d844838ab230080ab07cf0cc3566bb41d807c21bb9811284ea4"],"state_sha256":"bea34013b07c069e1b68c6ddd4a65baa23519b5aed70821d789f617b00cab843"}