{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ACBHUCGXZBSI24D74G5LGYIL57","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":"2c3213bc4e9b557378029e992701f2b1422fa2b5c5f2a43f4d7562a5e48067c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T09:23:26Z","title_canon_sha256":"418ce688f778ba91d54dc7173c7c930a32c6eadd51ed3dcc021d32fa6016d092"},"schema_version":"1.0","source":{"id":"2410.07745","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.07745","created_at":"2026-07-05T11:54:42Z"},{"alias_kind":"arxiv_version","alias_value":"2410.07745v4","created_at":"2026-07-05T11:54:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07745","created_at":"2026-07-05T11:54:42Z"},{"alias_kind":"pith_short_12","alias_value":"ACBHUCGXZBSI","created_at":"2026-07-05T11:54:42Z"},{"alias_kind":"pith_short_16","alias_value":"ACBHUCGXZBSI24D7","created_at":"2026-07-05T11:54:42Z"},{"alias_kind":"pith_short_8","alias_value":"ACBHUCGX","created_at":"2026-07-05T11:54:42Z"}],"graph_snapshots":[{"event_id":"sha256:b94cfc8f1093b3a5071610c29e871c4c389acd3be51c33bab638b68b97030538","target":"graph","created_at":"2026-07-05T11:54:42Z","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/2410.07745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite their powerful text generation capabilities, large language models (LLMs) still struggle to effectively utilize external tools to solve complex tasks, a challenge known as tool learning. Existing methods primarily rely on supervised fine-tuning, treating tool learning as a text generation problem while overlooking the decision-making complexities inherent in multi-step contexts. In this work, we propose modeling tool learning as a dynamic decision-making process and introduce StepTool, a novel step-grained reinforcement learning framework that enhances LLMs' capabilities in multi-step ","authors_text":"Chuhan Wu, Min Zhang, Shuai Wang, Weizhi Ma, Yuanqing Yu, Zhefan Wang, Zhiqiang Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T09:23:26Z","title":"StepTool: Enhancing Multi-Step Tool Usage in LLMs via Step-Grained Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07745","kind":"arxiv","version":4},"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:b4b3cbcec80b47647799ecbe1f6d782a4875a00c9296c8afda94aeae1b8ac440","target":"record","created_at":"2026-07-05T11:54:42Z","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":"2c3213bc4e9b557378029e992701f2b1422fa2b5c5f2a43f4d7562a5e48067c1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-10T09:23:26Z","title_canon_sha256":"418ce688f778ba91d54dc7173c7c930a32c6eadd51ed3dcc021d32fa6016d092"},"schema_version":"1.0","source":{"id":"2410.07745","kind":"arxiv","version":4}},"canonical_sha256":"00827a08d7c8648d707fe1bab3610befcddd07620b916d5c7ae9ee40bcd0cd7c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00827a08d7c8648d707fe1bab3610befcddd07620b916d5c7ae9ee40bcd0cd7c","first_computed_at":"2026-07-05T11:54:42.045633Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:54:42.045633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xp4fwKKGKzKkh4L3eTywKGMPYnvPbIh4YfOITG5OSrU6/3Mu2B21EKhIdENdQFCjhmn2Y3/01l73pSb8AczWCw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:54:42.046129Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.07745","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4b3cbcec80b47647799ecbe1f6d782a4875a00c9296c8afda94aeae1b8ac440","sha256:b94cfc8f1093b3a5071610c29e871c4c389acd3be51c33bab638b68b97030538"],"state_sha256":"7ab8eeeab1fec37148ef965ed1c0a54cc93931cd5a783aba3d15aa5f4e3a1953"}