{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L6GEWZBZRBZ6TIPSAQFXKWBOBK","short_pith_number":"pith:L6GEWZBZ","schema_version":"1.0","canonical_sha256":"5f8c4b64398873e9a1f2040b75582e0a9e6175edcb01be1c2c91109891e92204","source":{"kind":"arxiv","id":"2505.00024","version":2},"attestation_state":"computed","paper":{"title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Tao, Bryan Catanzaro, Guilin Liu, Jan Kautz, Jieyu Zhang, Qingyun Wu, Shaokun Zhang, Yi Dong, Zhiding Yu","submitted_at":"2025-04-25T02:55:21Z","abstract_excerpt":"Enabling large language models with external tools has become a pivotal strategy for extending their functionality beyond text space. To enhance LLMs' tool-calling abilities, previous approaches primarily rely on supervised fine-tuning (SFT) with trajectories distilled from stronger models, often resulting in imitative reasoning that limits generalization. In this work, we explore rule-based reinforcement learning to enhance tool-calling in LLMs, resulting in Nemotron-Research-Tool-N1, a series of tool-calling reasoning models. Rather than enforcing supervision over intermediate distilled reas"},"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":"2505.00024","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-04-25T02:55:21Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a44ae69794124753b53f962cf7a3a63aa8f53f2b93f71f623cc087b820f42025","abstract_canon_sha256":"01d5605f7ab5f98054f9e3c7fd230cde8b36ae5c4aa37b93c60008e6f13edd87"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:35.822914Z","signature_b64":"5JO8ZoOB+Hu6KOG0Po3BXDy554jQVppobYPP7PlvSOGsfwS2/Zb1vTIgFMssH9tnqHO1E66vHQoj/zXEP9wFDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f8c4b64398873e9a1f2040b75582e0a9e6175edcb01be1c2c91109891e92204","last_reissued_at":"2026-07-05T11:01:35.822448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:35.822448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrew Tao, Bryan Catanzaro, Guilin Liu, Jan Kautz, Jieyu Zhang, Qingyun Wu, Shaokun Zhang, Yi Dong, Zhiding Yu","submitted_at":"2025-04-25T02:55:21Z","abstract_excerpt":"Enabling large language models with external tools has become a pivotal strategy for extending their functionality beyond text space. To enhance LLMs' tool-calling abilities, previous approaches primarily rely on supervised fine-tuning (SFT) with trajectories distilled from stronger models, often resulting in imitative reasoning that limits generalization. In this work, we explore rule-based reinforcement learning to enhance tool-calling in LLMs, resulting in Nemotron-Research-Tool-N1, a series of tool-calling reasoning models. Rather than enforcing supervision over intermediate distilled reas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.00024","kind":"arxiv","version":2},"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/2505.00024/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":"2505.00024","created_at":"2026-07-05T11:01:35.822507+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.00024v2","created_at":"2026-07-05T11:01:35.822507+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.00024","created_at":"2026-07-05T11:01:35.822507+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6GEWZBZRBZ6","created_at":"2026-07-05T11:01:35.822507+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6GEWZBZRBZ6TIPS","created_at":"2026-07-05T11:01:35.822507+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6GEWZBZ","created_at":"2026-07-05T11:01:35.822507+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.20316","citing_title":"R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10875","citing_title":"Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09371","citing_title":"Capability-Aligned Hierarchical Learning for Tool-Augmented LLMs","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03892","citing_title":"Synthesize and Reward -- Reinforcement Learning for Multi-Step Tool Use in Live Environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00135","citing_title":"On Effectiveness and Efficiency of Agentic Tool-calling and RL Training","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29303","citing_title":"Entropy-KL Divergence-based Token Masking: A Novel Approach for Selective Fine-tuning of Large Language Models","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.06499","citing_title":"Webscale-RL: Automated Data Pipeline for Scaling RL Data to Pretraining Levels","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2511.07833","citing_title":"MURPHY: Feedback-Aware GRPO with Retrospective Credit Assignment for Multi-Turn Code Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11775","citing_title":"Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14126","citing_title":"Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11775","citing_title":"Entropy Polarity in Reinforcement Fine-Tuning: Direction, Asymmetry, and Control","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03476","citing_title":"CuraView: A Multi-Agent Framework for Medical Hallucination Detection with GraphRAG-Enhanced Knowledge Verification","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09730","citing_title":"RubricRefine: Improving Tool-Use Agent Reliability with Training-Free Pre-Execution Refinement","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20316","citing_title":"R2IF: Aligning Reasoning with Decisions via Composite Rewards for Interpretable LLM Function Calling","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09813","citing_title":"Controllable and Verifiable Tool-Use Data Synthesis for Agentic Reinforcement Learning","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09712","citing_title":"LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17739","citing_title":"Democratizing Tool Learning with Environments Fully Simulated by a Free 8B Language Model","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK","json":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK.json","graph_json":"https://pith.science/api/pith-number/L6GEWZBZRBZ6TIPSAQFXKWBOBK/graph.json","events_json":"https://pith.science/api/pith-number/L6GEWZBZRBZ6TIPSAQFXKWBOBK/events.json","paper":"https://pith.science/paper/L6GEWZBZ"},"agent_actions":{"view_html":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK","download_json":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK.json","view_paper":"https://pith.science/paper/L6GEWZBZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.00024&json=true","fetch_graph":"https://pith.science/api/pith-number/L6GEWZBZRBZ6TIPSAQFXKWBOBK/graph.json","fetch_events":"https://pith.science/api/pith-number/L6GEWZBZRBZ6TIPSAQFXKWBOBK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK/action/storage_attestation","attest_author":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK/action/author_attestation","sign_citation":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK/action/citation_signature","submit_replication":"https://pith.science/pith/L6GEWZBZRBZ6TIPSAQFXKWBOBK/action/replication_record"}},"created_at":"2026-07-05T11:01:35.822507+00:00","updated_at":"2026-07-05T11:01:35.822507+00:00"}