{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PTNQXGGL43Y6PFPS3UZ3LO6HT7","short_pith_number":"pith:PTNQXGGL","canonical_record":{"source":{"id":"2402.17574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T15:09:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ce7c26f137d63a08af78b5df62fbc7bbeda5b657c3ebcf3b12f60075f4212b32","abstract_canon_sha256":"4e33f656603aad176cdfb5d26506b101226b9c2a984a79ac945f94a94c63b2d2"},"schema_version":"1.0"},"canonical_sha256":"7cdb0b98cbe6f1e795f2dd33b5bbc79ff67ce63ed8b4f9972b341aee061acaf5","source":{"kind":"arxiv","id":"2402.17574","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17574","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17574v3","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17574","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"PTNQXGGL43Y6","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"PTNQXGGL43Y6PFPS","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"PTNQXGGL","created_at":"2026-07-05T08:28:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PTNQXGGL43Y6PFPS3UZ3LO6HT7","target":"record","payload":{"canonical_record":{"source":{"id":"2402.17574","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T15:09:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ce7c26f137d63a08af78b5df62fbc7bbeda5b657c3ebcf3b12f60075f4212b32","abstract_canon_sha256":"4e33f656603aad176cdfb5d26506b101226b9c2a984a79ac945f94a94c63b2d2"},"schema_version":"1.0"},"canonical_sha256":"7cdb0b98cbe6f1e795f2dd33b5bbc79ff67ce63ed8b4f9972b341aee061acaf5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:28:39.053374Z","signature_b64":"mFRSAfhjZdggUrkV+PqvkxpN83fZdgb6cKu9avwBGTThpD3vJkHAx7xo2YqEZNiRnzjL52yfY9jjS3Q2JAbdAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cdb0b98cbe6f1e795f2dd33b5bbc79ff67ce63ed8b4f9972b341aee061acaf5","last_reissued_at":"2026-07-05T08:28:39.052915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:28:39.052915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.17574","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TOXM2Jc7c/GGZ+tAtX4Q/1gUjKnO7zpHuyW7J6Ek1My/TPU+HF/M4225WFTr+hi4rIoGFaYdB7KPC6L5RAHLAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:01:29.371943Z"},"content_sha256":"d46222d1d37bbfc084a42740c36652cf64157c4fe6e49203eeacf7413818d9e8","schema_version":"1.0","event_id":"sha256:d46222d1d37bbfc084a42740c36652cf64157c4fe6e49203eeacf7413818d9e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PTNQXGGL43Y6PFPS3UZ3LO6HT7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Guiyang Hou, Hai Wu, Ke Tang, Mengna Wang, Peng Li, Weiming Lu, Wenqi Zhang, Yongliang Shen, Yueting Zhuang, Zeqi Tan","submitted_at":"2024-02-27T15:09:20Z","abstract_excerpt":"Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. However, most LLM-based agents are designed as specific task solvers with sophisticated prompt engineering, rather than agents capable of learning and evolving through interactions. These task solvers necessitate manually crafted prompts to inform task rules and regulate LLM behaviors, inherently incapacitating to address complex dynamic scenarios e.g., large interactive games. In light of this, we propose Agent-Pro: an LLM-based Agent with Policy-level Reflection and Optimization that can learn a wealt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17574","kind":"arxiv","version":3},"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/2402.17574/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:28:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hWMd4g39vKuYqxPBgyFDgtyRVx6Gi7Dr37TerytXRiiH56nfHerQqSEAXSLBisWp6vdk+jHoBq2420nRGUoSDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:01:29.372331Z"},"content_sha256":"16d0453081e5020c25d17a30f9503e2d2cc9e8eddcd9038027d8c1462f2c0e89","schema_version":"1.0","event_id":"sha256:16d0453081e5020c25d17a30f9503e2d2cc9e8eddcd9038027d8c1462f2c0e89"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PTNQXGGL43Y6PFPS3UZ3LO6HT7/bundle.json","state_url":"https://pith.science/pith/PTNQXGGL43Y6PFPS3UZ3LO6HT7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PTNQXGGL43Y6PFPS3UZ3LO6HT7/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-06T17:01:29Z","links":{"resolver":"https://pith.science/pith/PTNQXGGL43Y6PFPS3UZ3LO6HT7","bundle":"https://pith.science/pith/PTNQXGGL43Y6PFPS3UZ3LO6HT7/bundle.json","state":"https://pith.science/pith/PTNQXGGL43Y6PFPS3UZ3LO6HT7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PTNQXGGL43Y6PFPS3UZ3LO6HT7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PTNQXGGL43Y6PFPS3UZ3LO6HT7","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":"4e33f656603aad176cdfb5d26506b101226b9c2a984a79ac945f94a94c63b2d2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T15:09:20Z","title_canon_sha256":"ce7c26f137d63a08af78b5df62fbc7bbeda5b657c3ebcf3b12f60075f4212b32"},"schema_version":"1.0","source":{"id":"2402.17574","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.17574","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"arxiv_version","alias_value":"2402.17574v3","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.17574","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_12","alias_value":"PTNQXGGL43Y6","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_16","alias_value":"PTNQXGGL43Y6PFPS","created_at":"2026-07-05T08:28:39Z"},{"alias_kind":"pith_short_8","alias_value":"PTNQXGGL","created_at":"2026-07-05T08:28:39Z"}],"graph_snapshots":[{"event_id":"sha256:16d0453081e5020c25d17a30f9503e2d2cc9e8eddcd9038027d8c1462f2c0e89","target":"graph","created_at":"2026-07-05T08:28:39Z","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/2402.17574/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) exhibit robust problem-solving capabilities for diverse tasks. However, most LLM-based agents are designed as specific task solvers with sophisticated prompt engineering, rather than agents capable of learning and evolving through interactions. These task solvers necessitate manually crafted prompts to inform task rules and regulate LLM behaviors, inherently incapacitating to address complex dynamic scenarios e.g., large interactive games. In light of this, we propose Agent-Pro: an LLM-based Agent with Policy-level Reflection and Optimization that can learn a wealt","authors_text":"Guiyang Hou, Hai Wu, Ke Tang, Mengna Wang, Peng Li, Weiming Lu, Wenqi Zhang, Yongliang Shen, Yueting Zhuang, Zeqi Tan","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T15:09:20Z","title":"Agent-Pro: Learning to Evolve via Policy-Level Reflection and Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.17574","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:d46222d1d37bbfc084a42740c36652cf64157c4fe6e49203eeacf7413818d9e8","target":"record","created_at":"2026-07-05T08:28:39Z","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":"4e33f656603aad176cdfb5d26506b101226b9c2a984a79ac945f94a94c63b2d2","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-02-27T15:09:20Z","title_canon_sha256":"ce7c26f137d63a08af78b5df62fbc7bbeda5b657c3ebcf3b12f60075f4212b32"},"schema_version":"1.0","source":{"id":"2402.17574","kind":"arxiv","version":3}},"canonical_sha256":"7cdb0b98cbe6f1e795f2dd33b5bbc79ff67ce63ed8b4f9972b341aee061acaf5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cdb0b98cbe6f1e795f2dd33b5bbc79ff67ce63ed8b4f9972b341aee061acaf5","first_computed_at":"2026-07-05T08:28:39.052915Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:39.052915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mFRSAfhjZdggUrkV+PqvkxpN83fZdgb6cKu9avwBGTThpD3vJkHAx7xo2YqEZNiRnzjL52yfY9jjS3Q2JAbdAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:39.053374Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.17574","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d46222d1d37bbfc084a42740c36652cf64157c4fe6e49203eeacf7413818d9e8","sha256:16d0453081e5020c25d17a30f9503e2d2cc9e8eddcd9038027d8c1462f2c0e89"],"state_sha256":"79bdfd74909af8cc51e0c93ac269a8b098557564757237022cd6da7b7e935104"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WuhPzRUC3aXyqUWDxNvan46zSonbrEsvwrMjsPo39C1jrS73WudWmBDfmkdFk4Vfo8Htsdh3wVFFXM0I22ZqBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:01:29.374177Z","bundle_sha256":"c077039f57d624c6e13e120f74f8f5901ea4bcc8bf141fab58aea0bc3c5ace05"}}