{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:F4YQDNY3WDYU6D32Q7D3PI7EZA","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":"fb2610e1143e53dc7035b94ee9e1cf93f340dda4df32e3a24c1b162c5c463ec5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T06:19:50Z","title_canon_sha256":"81c6b9f878625f5f731d5e5e630c72a5ed4ff64d1074a30ced0368358f264e18"},"schema_version":"1.0","source":{"id":"2508.19598","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.19598","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"arxiv_version","alias_value":"2508.19598v1","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.19598","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"pith_short_12","alias_value":"F4YQDNY3WDYU","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"pith_short_16","alias_value":"F4YQDNY3WDYU6D32","created_at":"2026-07-05T12:00:14Z"},{"alias_kind":"pith_short_8","alias_value":"F4YQDNY3","created_at":"2026-07-05T12:00:14Z"}],"graph_snapshots":[{"event_id":"sha256:f007464705596f385f87bb859b17162b1b1dc07174deeca51753e79a366143e3","target":"graph","created_at":"2026-07-05T12:00:14Z","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/2508.19598/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Wenqing Wang, Yong Hu, Zhiwei Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T06:19:50Z","title":"Encouraging Good Processes Without the Need for Good Answers: Reinforcement Learning for LLM Agent Planning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.19598","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":"sha256:528fbc64e30b3ff635ce58d821f2c2fb37b53c7b26b25a8f2bd774d277ce61f0","target":"record","created_at":"2026-07-05T12:00:14Z","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":"fb2610e1143e53dc7035b94ee9e1cf93f340dda4df32e3a24c1b162c5c463ec5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-27T06:19:50Z","title_canon_sha256":"81c6b9f878625f5f731d5e5e630c72a5ed4ff64d1074a30ced0368358f264e18"},"schema_version":"1.0","source":{"id":"2508.19598","kind":"arxiv","version":1}},"canonical_sha256":"2f3101b71bb0f14f0f7a87c7b7a3e4c830bd38cdc37d2b1dc4fcfbd7acf0c77f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f3101b71bb0f14f0f7a87c7b7a3e4c830bd38cdc37d2b1dc4fcfbd7acf0c77f","first_computed_at":"2026-07-05T12:00:14.782120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:14.782120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h97B62rxa1aGcl/ynzBpgtLOKEhSdlwvQPzUi2PPoyAey7GqdvUQCDpMlw8rR07I2LaXXmu5By6q4fZldJTGCw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:14.782601Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.19598","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:528fbc64e30b3ff635ce58d821f2c2fb37b53c7b26b25a8f2bd774d277ce61f0","sha256:f007464705596f385f87bb859b17162b1b1dc07174deeca51753e79a366143e3"],"state_sha256":"cf910027cacc8546355f5bc6d1431cefba4a907b814dfefe746d338f5699c5d1"}