{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HPM62MZJJV2Y45IOV3J26VEPNS","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":"2f2e808af5be9edf302edd28ba04b7655690228493fb683903b5ed585aa52c80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T18:49:25Z","title_canon_sha256":"322913e80ddabc915df10eb3b1a4668df4aadebc1d1a69e2fcef21a91a57f3d6"},"schema_version":"1.0","source":{"id":"2502.12130","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.12130","created_at":"2026-07-05T10:15:39Z"},{"alias_kind":"arxiv_version","alias_value":"2502.12130v1","created_at":"2026-07-05T10:15:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12130","created_at":"2026-07-05T10:15:39Z"},{"alias_kind":"pith_short_12","alias_value":"HPM62MZJJV2Y","created_at":"2026-07-05T10:15:39Z"},{"alias_kind":"pith_short_16","alias_value":"HPM62MZJJV2Y45IO","created_at":"2026-07-05T10:15:39Z"},{"alias_kind":"pith_short_8","alias_value":"HPM62MZJ","created_at":"2026-07-05T10:15:39Z"}],"graph_snapshots":[{"event_id":"sha256:864da3ffefa9c9f5507430f0970cd16cc1096fab62d749a175705229e4e0c87b","target":"graph","created_at":"2026-07-05T10:15:39Z","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/2502.12130/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have demonstrated remarkable capabilities across a range of text-generation tasks. However, LLMs still struggle with problems requiring multi-step decision-making and environmental feedback, such as online shopping, scientific reasoning, and mathematical problem-solving. Unlike pure text data, collecting large-scale decision-making data is challenging. Moreover, many powerful LLMs are only accessible through APIs, which hinders their fine-tuning for agent tasks due to cost and complexity. To address LLM agents' limitations, we propose a framework that can automatic","authors_text":"Chuang Gan, Delin Chen, Rui Sun, Wenjun Liu, Zhenfang Chen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T18:49:25Z","title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12130","kind":"arxiv","version":1},"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":"sha256:9ce6e06b552bb85d96a0569a8411f7a12311d8fb5bb75b7fc9870d54745bd484","target":"record","created_at":"2026-07-05T10:15:39Z","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":"2f2e808af5be9edf302edd28ba04b7655690228493fb683903b5ed585aa52c80","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T18:49:25Z","title_canon_sha256":"322913e80ddabc915df10eb3b1a4668df4aadebc1d1a69e2fcef21a91a57f3d6"},"schema_version":"1.0","source":{"id":"2502.12130","kind":"arxiv","version":1}},"canonical_sha256":"3bd9ed33294d758e750eaed3af548f6caff0e014668d9cafc0b21bccb0d8ee54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bd9ed33294d758e750eaed3af548f6caff0e014668d9cafc0b21bccb0d8ee54","first_computed_at":"2026-07-05T10:15:39.459083Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:15:39.459083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h0bEmVt2Ydh+pfrqfhMV0jmstJcVVS0596KZ1I5aOUMUc4BItrwY/hnmfpyIKVmPqMSWdc3cl8odN1Ex6cklAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:15:39.459738Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.12130","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9ce6e06b552bb85d96a0569a8411f7a12311d8fb5bb75b7fc9870d54745bd484","sha256:864da3ffefa9c9f5507430f0970cd16cc1096fab62d749a175705229e4e0c87b"],"state_sha256":"e568e9ad7f3a9761d5de13644195f3830082e68c0b5bc4911313761b9e0f168c"}