{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HPM62MZJJV2Y45IOV3J26VEPNS","short_pith_number":"pith:HPM62MZJ","schema_version":"1.0","canonical_sha256":"3bd9ed33294d758e750eaed3af548f6caff0e014668d9cafc0b21bccb0d8ee54","source":{"kind":"arxiv","id":"2502.12130","version":1},"attestation_state":"computed","paper":{"title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chuang Gan, Delin Chen, Rui Sun, Wenjun Liu, Zhenfang Chen","submitted_at":"2025-02-17T18:49:25Z","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"},"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":"2502.12130","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-17T18:49:25Z","cross_cats_sorted":[],"title_canon_sha256":"322913e80ddabc915df10eb3b1a4668df4aadebc1d1a69e2fcef21a91a57f3d6","abstract_canon_sha256":"2f2e808af5be9edf302edd28ba04b7655690228493fb683903b5ed585aa52c80"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:15:39.459738Z","signature_b64":"h0bEmVt2Ydh+pfrqfhMV0jmstJcVVS0596KZ1I5aOUMUc4BItrwY/hnmfpyIKVmPqMSWdc3cl8odN1Ex6cklAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bd9ed33294d758e750eaed3af548f6caff0e014668d9cafc0b21bccb0d8ee54","last_reissued_at":"2026-07-05T10:15:39.459083Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:15:39.459083Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Scaling Autonomous Agents via Automatic Reward Modeling And Planning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chuang Gan, Delin Chen, Rui Sun, Wenjun Liu, Zhenfang Chen","submitted_at":"2025-02-17T18:49:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.12130","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/2502.12130/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":"2502.12130","created_at":"2026-07-05T10:15:39.459166+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.12130v1","created_at":"2026-07-05T10:15:39.459166+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.12130","created_at":"2026-07-05T10:15:39.459166+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPM62MZJJV2Y","created_at":"2026-07-05T10:15:39.459166+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPM62MZJJV2Y45IO","created_at":"2026-07-05T10:15:39.459166+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPM62MZJ","created_at":"2026-07-05T10:15:39.459166+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.01990","citing_title":"Advances and Challenges in Foundation Agents: From Brain-Inspired Intelligence to Evolutionary, Collaborative, and Safe Systems","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":189,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS","json":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS.json","graph_json":"https://pith.science/api/pith-number/HPM62MZJJV2Y45IOV3J26VEPNS/graph.json","events_json":"https://pith.science/api/pith-number/HPM62MZJJV2Y45IOV3J26VEPNS/events.json","paper":"https://pith.science/paper/HPM62MZJ"},"agent_actions":{"view_html":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS","download_json":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS.json","view_paper":"https://pith.science/paper/HPM62MZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.12130&json=true","fetch_graph":"https://pith.science/api/pith-number/HPM62MZJJV2Y45IOV3J26VEPNS/graph.json","fetch_events":"https://pith.science/api/pith-number/HPM62MZJJV2Y45IOV3J26VEPNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS/action/storage_attestation","attest_author":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS/action/author_attestation","sign_citation":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS/action/citation_signature","submit_replication":"https://pith.science/pith/HPM62MZJJV2Y45IOV3J26VEPNS/action/replication_record"}},"created_at":"2026-07-05T10:15:39.459166+00:00","updated_at":"2026-07-05T10:15:39.459166+00:00"}