{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3GMEITB4M7PCWYVJ7LBWZNEMWY","short_pith_number":"pith:3GMEITB4","schema_version":"1.0","canonical_sha256":"d998444c3c67de2b62a9fac36cb48cb61a3f54c37f8d944e3c979d769d8dbca3","source":{"kind":"arxiv","id":"2508.19506","version":1},"attestation_state":"computed","paper":{"title":"Learning Game-Playing Agents with Generative Code Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Allen Nie, Ryan Rong, YuCheng Yuan, Zhiyi Kuang","submitted_at":"2025-08-27T01:30:20Z","abstract_excerpt":"We present a generative optimization approach for learning game-playing agents, where policies are represented as Python programs and refined using large language models (LLMs). Our method treats decision-making policies as self-evolving code, with current observation as input and an in-game action as output, enabling agents to self-improve through execution traces and natural language feedback with minimal human intervention. Applied to Atari games, our game-playing Python program achieves performance competitive with deep reinforcement learning (RL) baselines while using significantly less t"},"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":"2508.19506","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T01:30:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3916256f0961aa655eaa0ca8eb549b249f67d759eefe87af9e6c662da0f917c6","abstract_canon_sha256":"a22fe36e2b9c2a29c66b776555f6dd8399badc937633b4c8cd488ebb31581d10"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:12.798009Z","signature_b64":"20aXdTE00MTN8VDghHGgr5x/mvoIrtRMdkxePywLL+PK4v8O/Ieo7AdBh7XvehJIVPdjdEYpshiXgVl/12xkCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d998444c3c67de2b62a9fac36cb48cb61a3f54c37f8d944e3c979d769d8dbca3","last_reissued_at":"2026-07-05T12:00:12.797595Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:12.797595Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Game-Playing Agents with Generative Code Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Allen Nie, Ryan Rong, YuCheng Yuan, Zhiyi Kuang","submitted_at":"2025-08-27T01:30:20Z","abstract_excerpt":"We present a generative optimization approach for learning game-playing agents, where policies are represented as Python programs and refined using large language models (LLMs). Our method treats decision-making policies as self-evolving code, with current observation as input and an in-game action as output, enabling agents to self-improve through execution traces and natural language feedback with minimal human intervention. Applied to Atari games, our game-playing Python program achieves performance competitive with deep reinforcement learning (RL) baselines while using significantly less t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19506","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/2508.19506/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":"2508.19506","created_at":"2026-07-05T12:00:12.797654+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19506v1","created_at":"2026-07-05T12:00:12.797654+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19506","created_at":"2026-07-05T12:00:12.797654+00:00"},{"alias_kind":"pith_short_12","alias_value":"3GMEITB4M7PC","created_at":"2026-07-05T12:00:12.797654+00:00"},{"alias_kind":"pith_short_16","alias_value":"3GMEITB4M7PCWYVJ","created_at":"2026-07-05T12:00:12.797654+00:00"},{"alias_kind":"pith_short_8","alias_value":"3GMEITB4","created_at":"2026-07-05T12:00:12.797654+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY","json":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY.json","graph_json":"https://pith.science/api/pith-number/3GMEITB4M7PCWYVJ7LBWZNEMWY/graph.json","events_json":"https://pith.science/api/pith-number/3GMEITB4M7PCWYVJ7LBWZNEMWY/events.json","paper":"https://pith.science/paper/3GMEITB4"},"agent_actions":{"view_html":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY","download_json":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY.json","view_paper":"https://pith.science/paper/3GMEITB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19506&json=true","fetch_graph":"https://pith.science/api/pith-number/3GMEITB4M7PCWYVJ7LBWZNEMWY/graph.json","fetch_events":"https://pith.science/api/pith-number/3GMEITB4M7PCWYVJ7LBWZNEMWY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/action/storage_attestation","attest_author":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/action/author_attestation","sign_citation":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/action/citation_signature","submit_replication":"https://pith.science/pith/3GMEITB4M7PCWYVJ7LBWZNEMWY/action/replication_record"}},"created_at":"2026-07-05T12:00:12.797654+00:00","updated_at":"2026-07-05T12:00:12.797654+00:00"}