{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:F4YQDNY3WDYU6D32Q7D3PI7EZA","short_pith_number":"pith:F4YQDNY3","schema_version":"1.0","canonical_sha256":"2f3101b71bb0f14f0f7a87c7b7a3e4c830bd38cdc37d2b1dc4fcfbd7acf0c77f","source":{"kind":"arxiv","id":"2508.19598","version":1},"attestation_state":"computed","paper":{"title":"Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Wenqing Wang, Yong Hu, Zhiwei Li","submitted_at":"2025-08-27T06:19:50Z","abstract_excerpt":"The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However, prevailing training paradigms employ end-to-end, multi-objective optimization that jointly trains both capabilities. This paradigm faces two critical challenges: imbalanced optimization objective allocation and scarcity of verifiable data, making it difficult to enhance the agent's planning capability. To address these challenges, we propose Reinforcement L"},"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":"2508.19598","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T06:19:50Z","cross_cats_sorted":[],"title_canon_sha256":"81c6b9f878625f5f731d5e5e630c72a5ed4ff64d1074a30ced0368358f264e18","abstract_canon_sha256":"fb2610e1143e53dc7035b94ee9e1cf93f340dda4df32e3a24c1b162c5c463ec5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:00:14.782601Z","signature_b64":"h97B62rxa1aGcl/ynzBpgtLOKEhSdlwvQPzUi2PPoyAey7GqdvUQCDpMlw8rR07I2LaXXmu5By6q4fZldJTGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f3101b71bb0f14f0f7a87c7b7a3e4c830bd38cdc37d2b1dc4fcfbd7acf0c77f","last_reissued_at":"2026-07-05T12:00:14.782120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:00:14.782120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Wenqing Wang, Yong Hu, Zhiwei Li","submitted_at":"2025-08-27T06:19:50Z","abstract_excerpt":"The functionality of Large Language Model (LLM) agents is primarily determined by two capabilities: action planning and answer summarization. The former, action planning, is the core capability that dictates an agent's performance. However, prevailing training paradigms employ end-to-end, multi-objective optimization that jointly trains both capabilities. This paradigm faces two critical challenges: imbalanced optimization objective allocation and scarcity of verifiable data, making it difficult to enhance the agent's planning capability. To address these challenges, we propose Reinforcement L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19598","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/2508.19598/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":"2508.19598","created_at":"2026-07-05T12:00:14.782176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.19598v1","created_at":"2026-07-05T12:00:14.782176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19598","created_at":"2026-07-05T12:00:14.782176+00:00"},{"alias_kind":"pith_short_12","alias_value":"F4YQDNY3WDYU","created_at":"2026-07-05T12:00:14.782176+00:00"},{"alias_kind":"pith_short_16","alias_value":"F4YQDNY3WDYU6D32","created_at":"2026-07-05T12:00:14.782176+00:00"},{"alias_kind":"pith_short_8","alias_value":"F4YQDNY3","created_at":"2026-07-05T12:00:14.782176+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07435","citing_title":"RLVP: Penalize the Path, Reward the Outcome","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06534","citing_title":"ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2509.08827","citing_title":"A Survey of Reinforcement Learning for Large Reasoning Models","ref_index":295,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06534","citing_title":"ROSE: Rollout On Serving GPUs via Cooperative Elasticity for Agentic RL","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA","json":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA.json","graph_json":"https://pith.science/api/pith-number/F4YQDNY3WDYU6D32Q7D3PI7EZA/graph.json","events_json":"https://pith.science/api/pith-number/F4YQDNY3WDYU6D32Q7D3PI7EZA/events.json","paper":"https://pith.science/paper/F4YQDNY3"},"agent_actions":{"view_html":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA","download_json":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA.json","view_paper":"https://pith.science/paper/F4YQDNY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.19598&json=true","fetch_graph":"https://pith.science/api/pith-number/F4YQDNY3WDYU6D32Q7D3PI7EZA/graph.json","fetch_events":"https://pith.science/api/pith-number/F4YQDNY3WDYU6D32Q7D3PI7EZA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA/action/storage_attestation","attest_author":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA/action/author_attestation","sign_citation":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA/action/citation_signature","submit_replication":"https://pith.science/pith/F4YQDNY3WDYU6D32Q7D3PI7EZA/action/replication_record"}},"created_at":"2026-07-05T12:00:14.782176+00:00","updated_at":"2026-07-05T12:00:14.782176+00:00"}