{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:V72V276Z3V76P34K6GVQEF3CKK","short_pith_number":"pith:V72V276Z","schema_version":"1.0","canonical_sha256":"aff55d7fd9dd7fe7ef8af1ab02176252abb362f775883e2f74d2dca075d5813b","source":{"kind":"arxiv","id":"2605.29568","version":1},"attestation_state":"computed","paper":{"title":"DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bibo Cai, Bing Qin, Kai Xiong, Ting Liu, Xiao Ding, Yang He, Yufei Zhang, Zhouhao Sun","submitted_at":"2026-05-28T08:17:20Z","abstract_excerpt":"Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-correction. While RL mitigates this, conventional approaches for Tool-Integrated Reasoning are hindered by sparse outcome-based rewards, failing to supervise intermediate reasoning steps and tool invocations. To address this, we propose DeepTool, a novel framework that scales deliberate thinking within the interleaved process of thinking, action, and observation at each turn. In D"},"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":"2605.29568","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-05-28T08:17:20Z","cross_cats_sorted":[],"title_canon_sha256":"f7a603eb66f2ca5ef30902437c25dd7595d7ef0d0c02d773dff33ffd45ca52fd","abstract_canon_sha256":"efab71cf336baf47fd828d12d1c9022a4cc334e8dc83efa386afed7ac65b49dc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:05:47.892582Z","signature_b64":"NPzeQrU32mHCu8mMIeXqq/bNSmgsJIoToA7C0/c0IuOPuqv7OdDwX1CXbAHEbsUiDOoyuLX/Pl0Z9eSPbtizAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aff55d7fd9dd7fe7ef8af1ab02176252abb362f775883e2f74d2dca075d5813b","last_reissued_at":"2026-05-29T01:05:47.891767Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:05:47.891767Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepTool: Scaling Interleaved Deliberation in Tool-Integrated Reasoning via Process-Supervised Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Bibo Cai, Bing Qin, Kai Xiong, Ting Liu, Xiao Ding, Yang He, Yufei Zhang, Zhouhao Sun","submitted_at":"2026-05-28T08:17:20Z","abstract_excerpt":"Tool-Integrated Reasoning (TIR) extends LLM capabilities by leveraging external environments. However, existing methods lack the deliberation during sequential tool invocation required for strategic planning and self-correction. While RL mitigates this, conventional approaches for Tool-Integrated Reasoning are hindered by sparse outcome-based rewards, failing to supervise intermediate reasoning steps and tool invocations. To address this, we propose DeepTool, a novel framework that scales deliberate thinking within the interleaved process of thinking, action, and observation at each turn. In D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.29568","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/2605.29568/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":"2605.29568","created_at":"2026-05-29T01:05:47.891896+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.29568v1","created_at":"2026-05-29T01:05:47.891896+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.29568","created_at":"2026-05-29T01:05:47.891896+00:00"},{"alias_kind":"pith_short_12","alias_value":"V72V276Z3V76","created_at":"2026-05-29T01:05:47.891896+00:00"},{"alias_kind":"pith_short_16","alias_value":"V72V276Z3V76P34K","created_at":"2026-05-29T01:05:47.891896+00:00"},{"alias_kind":"pith_short_8","alias_value":"V72V276Z","created_at":"2026-05-29T01:05:47.891896+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK","json":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK.json","graph_json":"https://pith.science/api/pith-number/V72V276Z3V76P34K6GVQEF3CKK/graph.json","events_json":"https://pith.science/api/pith-number/V72V276Z3V76P34K6GVQEF3CKK/events.json","paper":"https://pith.science/paper/V72V276Z"},"agent_actions":{"view_html":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK","download_json":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK.json","view_paper":"https://pith.science/paper/V72V276Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.29568&json=true","fetch_graph":"https://pith.science/api/pith-number/V72V276Z3V76P34K6GVQEF3CKK/graph.json","fetch_events":"https://pith.science/api/pith-number/V72V276Z3V76P34K6GVQEF3CKK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK/action/storage_attestation","attest_author":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK/action/author_attestation","sign_citation":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK/action/citation_signature","submit_replication":"https://pith.science/pith/V72V276Z3V76P34K6GVQEF3CKK/action/replication_record"}},"created_at":"2026-05-29T01:05:47.891896+00:00","updated_at":"2026-05-29T01:05:47.891896+00:00"}