{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:24T2PMM64YGHAYX6DWUVHYS7J2","short_pith_number":"pith:24T2PMM6","schema_version":"1.0","canonical_sha256":"d727a7b19ee60c7062fe1da953e25f4eb5cbd43f703157df9cc1d4a9c8d39ae5","source":{"kind":"arxiv","id":"2508.00344","version":5},"attestation_state":"computed","paper":{"title":"PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Cui, Chong Chen, Keer Lu, Wentao Zhang, Yunhuai Liu","submitted_at":"2025-08-01T06:17:11Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces challenges when deploying LLMs in agent-based environments. The widely adopted agent paradigm ReAct centers on integrating single-step reasoning with immediate action execution, which limits its effectiveness in complex tasks requiring long-term strategic planning. Furthermore, the coordination between the planner and executor during problem-solving is also a critical factor to consider in agent design. Additionally, current approaches predominantly rel"},"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":"2508.00344","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T06:17:11Z","cross_cats_sorted":[],"title_canon_sha256":"4ea4ee310949bd021c90ebba5aabd3adf6bf058dc6e1a9e30159b3e01b54349d","abstract_canon_sha256":"44ecfaff76eac19002fd4d77c0c386b0a0dde621deb147c00122ad045365b5d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:24:24.529719Z","signature_b64":"+4vWFLVP01skXlwXahUy4VzWNtF7a2piiaV/7j+KgyGaN0RoVxwb0ncrQqDkbvWqTgUCw4VOmeKYsvduRIHFAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d727a7b19ee60c7062fe1da953e25f4eb5cbd43f703157df9cc1d4a9c8d39ae5","last_reissued_at":"2026-07-29T01:24:24.528760Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:24:24.528760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PilotRL: Training Language Model Agents via Global Planning-Guided Progressive Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Cui, Chong Chen, Keer Lu, Wentao Zhang, Yunhuai Liu","submitted_at":"2025-08-01T06:17:11Z","abstract_excerpt":"Large Language Models (LLMs) have shown remarkable advancements in tackling agent-oriented tasks. Despite their potential, existing work faces challenges when deploying LLMs in agent-based environments. The widely adopted agent paradigm ReAct centers on integrating single-step reasoning with immediate action execution, which limits its effectiveness in complex tasks requiring long-term strategic planning. Furthermore, the coordination between the planner and executor during problem-solving is also a critical factor to consider in agent design. Additionally, current approaches predominantly rel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00344","kind":"arxiv","version":5},"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/2508.00344/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":"2508.00344","created_at":"2026-07-29T01:24:24.529199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00344v5","created_at":"2026-07-29T01:24:24.529199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00344","created_at":"2026-07-29T01:24:24.529199+00:00"},{"alias_kind":"pith_short_12","alias_value":"24T2PMM64YGH","created_at":"2026-07-29T01:24:24.529199+00:00"},{"alias_kind":"pith_short_16","alias_value":"24T2PMM64YGHAYX6","created_at":"2026-07-29T01:24:24.529199+00:00"},{"alias_kind":"pith_short_8","alias_value":"24T2PMM6","created_at":"2026-07-29T01:24:24.529199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2607.01764","citing_title":"Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2606.12384","citing_title":"APPO: Agentic Procedural Policy Optimization","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12943","citing_title":"Reinforced Collaboration in Multi-Agent Flow Networks","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":53,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09459","citing_title":"From Reasoning to Agentic: Credit Assignment in Reinforcement Learning for Large Language Models","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07774","citing_title":"RoboAgent: Chaining Basic Capabilities for Embodied Task Planning","ref_index":64,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2","json":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2.json","graph_json":"https://pith.science/api/pith-number/24T2PMM64YGHAYX6DWUVHYS7J2/graph.json","events_json":"https://pith.science/api/pith-number/24T2PMM64YGHAYX6DWUVHYS7J2/events.json","paper":"https://pith.science/paper/24T2PMM6"},"agent_actions":{"view_html":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2","download_json":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2.json","view_paper":"https://pith.science/paper/24T2PMM6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00344&json=true","fetch_graph":"https://pith.science/api/pith-number/24T2PMM64YGHAYX6DWUVHYS7J2/graph.json","fetch_events":"https://pith.science/api/pith-number/24T2PMM64YGHAYX6DWUVHYS7J2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2/action/storage_attestation","attest_author":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2/action/author_attestation","sign_citation":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2/action/citation_signature","submit_replication":"https://pith.science/pith/24T2PMM64YGHAYX6DWUVHYS7J2/action/replication_record"}},"created_at":"2026-07-29T01:24:24.529199+00:00","updated_at":"2026-07-29T01:24:24.529199+00:00"}