{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:IPDYF7WAL2JQY73ECA6M6ZKLS7","short_pith_number":"pith:IPDYF7WA","schema_version":"1.0","canonical_sha256":"43c782fec05e930c7f64103ccf654b97d85382871ba7af91c76cfd7468ad415a","source":{"kind":"arxiv","id":"2306.05301","version":2},"attestation_state":"computed","paper":{"title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Compact language models can learn to use new real-world tools by training on simulated multi-agent interactions.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boxi Cao, Hongyu Lin, Le Sun, Qiao Liang, Qiaoyu Tang, Xianpei Han, Ziliang Deng","submitted_at":"2023-06-08T15:46:32Z","abstract_excerpt":"Enabling large language models to utilize real-world tools effectively is crucial for achieving embodied intelligence. Existing approaches to tool learning have either primarily relied on extremely large language models, such as GPT-4, to attain generalized tool-use abilities in a zero-shot manner, or utilized supervised learning to train limited scopes of tools on compact models. However, it remains uncertain whether smaller language models can achieve generalized tool-use abilities without tool-specific training. To address this question, this paper introduces ToolAlpaca, a novel framework 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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2306.05301","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-08T15:46:32Z","cross_cats_sorted":[],"title_canon_sha256":"512f61380dab930691294793664126497ef486c232611cee5338df827f315f40","abstract_canon_sha256":"9c9c6a40f471db00bc795491a595370a6b25f237c8ce7cac442ef63a1e1bb3ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:49.853803Z","signature_b64":"ylXMI9O0apk2gHN9941PpGq55A/UGX2/bA3HPvTzkE60KGBSqNOkhohGX7tSZcTEdLsMEWar6VGyOZ/hZmaUAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43c782fec05e930c7f64103ccf654b97d85382871ba7af91c76cfd7468ad415a","last_reissued_at":"2026-05-17T23:38:49.853235Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:49.853235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Compact language models can learn to use new real-world tools by training on simulated multi-agent interactions.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Boxi Cao, Hongyu Lin, Le Sun, Qiao Liang, Qiaoyu Tang, Xianpei Han, Ziliang Deng","submitted_at":"2023-06-08T15:46:32Z","abstract_excerpt":"Enabling large language models to utilize real-world tools effectively is crucial for achieving embodied intelligence. Existing approaches to tool learning have either primarily relied on extremely large language models, such as GPT-4, to attain generalized tool-use abilities in a zero-shot manner, or utilized supervised learning to train limited scopes of tools on compact models. However, it remains uncertain whether smaller language models can achieve generalized tool-use abilities without tool-specific training. To address this question, this paper introduces ToolAlpaca, a novel framework d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experimental results demonstrate that ToolAlpaca achieves effective generalized tool-use capabilities comparable to those of extremely large language models like GPT-3.5, demonstrating that learning generalized tool-use ability is feasible for compact language models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The simulated multi-agent interactions produce training data whose distribution is close enough to real-world tool use that fine-tuned models generalize to unseen APIs without additional per-tool supervision.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ToolAlpaca trains 7B and 13B models on 3938 simulated tool-use cases to reach generalized tool-use performance comparable to GPT-3.5 on unseen APIs.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Compact language models can learn to use new real-world tools by training on simulated multi-agent interactions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"c03b8e867060ecd148fde9265f234cd5d4226ebfdcfd600b990dab9c82d2d9c4"},"source":{"id":"2306.05301","kind":"arxiv","version":2},"verdict":{"id":"dbd30bb2-7336-4641-8cf6-00bdd5144a9e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T22:59:52.482884Z","strongest_claim":"Experimental results demonstrate that ToolAlpaca achieves effective generalized tool-use capabilities comparable to those of extremely large language models like GPT-3.5, demonstrating that learning generalized tool-use ability is feasible for compact language models.","one_line_summary":"ToolAlpaca trains 7B and 13B models on 3938 simulated tool-use cases to reach generalized tool-use performance comparable to GPT-3.5 on unseen APIs.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The simulated multi-agent interactions produce training data whose distribution is close enough to real-world tool use that fine-tuned models generalize to unseen APIs without additional per-tool supervision.","pith_extraction_headline":"Compact language models can learn to use new real-world tools by training on simulated multi-agent interactions."},"references":{"count":34,"sample":[{"doi":"","year":2023,"title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","work_id":"a20d9332-ab34-485c-a060-1ba47cc98930","ref_index":1,"cited_arxiv_id":"2304.08244","is_internal_anchor":true},{"doi":"","year":2023,"title":"HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face","work_id":"f20ed1da-2676-4598-a11b-54549718735b","ref_index":2,"cited_arxiv_id":"2303.17580","is_internal_anchor":true},{"doi":"","year":2023,"title":"On the tool manipulation capability of open-source large language models.arXiv preprint arXiv:2305.16504(2023)","work_id":"18febc22-221f-4db2-8168-15e148f613c3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Write a general overview of the API 's purpose and functionality","work_id":"4f28c4cb-f1aa-4915-97eb-fe1ba788466e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"List and briefly describe all features provided by the API, ensuring each feature has a clear and distinct purpose with low coupling between them","work_id":"ed0e44bb-d435-423f-a67e-eb9b69f7ea8e","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":34,"snapshot_sha256":"25d4d992dc8065cdcfcf4029f83dbf3cdb6812c2d13360a181c9ed5fed450295","internal_anchors":2},"formal_canon":{"evidence_count":2,"snapshot_sha256":"45df9e96c87c60b8217f373fb1c05b4802bb4e1df63fd97a244959507511895e"},"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":"2306.05301","created_at":"2026-05-17T23:38:49.853333+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.05301v2","created_at":"2026-05-17T23:38:49.853333+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.05301","created_at":"2026-05-17T23:38:49.853333+00:00"},{"alias_kind":"pith_short_12","alias_value":"IPDYF7WAL2JQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"IPDYF7WAL2JQY73E","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"IPDYF7WA","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":37,"internal_anchor_count":37,"sample":[{"citing_arxiv_id":"2409.00557","citing_title":"Learning to Ask: When LLM Agents Meet Unclear Instruction","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":152,"is_internal_anchor":true},{"citing_arxiv_id":"2503.22693","citing_title":"Bridging Language Models and Financial Analysis","ref_index":97,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06597","citing_title":"UniSD: Towards a Unified Self-Distillation Framework for Large Language Models","ref_index":29,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22177","citing_title":"Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22564","citing_title":"SynAE: A Framework for Measuring the Quality of Synthetic Data for Tool-Calling Agent Evaluations","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09817","citing_title":"Evaluating Tool Cloning in Agentic-AI Ecosystems","ref_index":66,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16508","citing_title":"The Scaling Laws of Skills in LLM Agent Systems","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18930","citing_title":"OEP: Poisoning Self-Evolving LLM Agents via Locally Correct but Non-Transferable Experiences","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17558","citing_title":"Firefly: Illuminating Large-Scale Verified Tool-Call Data Generation from Real APIs","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2508.08791","citing_title":"Feedback-Driven Tool-Use Improvements in Large Language Models via Automated Build Environments","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2510.14703","citing_title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2601.12538","citing_title":"Agentic Reasoning for Large Language Models","ref_index":205,"is_internal_anchor":true},{"citing_arxiv_id":"2309.02427","citing_title":"Cognitive Architectures for Language Agents","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05353","citing_title":"AgentXRay: White-Boxing Agentic Systems via Workflow Reconstruction","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06185","citing_title":"Benchmarking LLM Tool-Use in the Wild","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2304.08244","citing_title":"API-Bank: A Comprehensive Benchmark for Tool-Augmented LLMs","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2603.24709","citing_title":"Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02022","citing_title":"ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12652","citing_title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","ref_index":76,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06387","citing_title":"Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02022","citing_title":"ATBench: A Diverse and Realistic Agent Trajectory Benchmark for Safety Evaluation and Diagnosis","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03057","citing_title":"Querying Structured Data Through Natural Language Using Language Models","ref_index":16,"is_internal_anchor":true},{"citing_arxiv_id":"2406.13352","citing_title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","ref_index":54,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7","json":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7.json","graph_json":"https://pith.science/api/pith-number/IPDYF7WAL2JQY73ECA6M6ZKLS7/graph.json","events_json":"https://pith.science/api/pith-number/IPDYF7WAL2JQY73ECA6M6ZKLS7/events.json","paper":"https://pith.science/paper/IPDYF7WA"},"agent_actions":{"view_html":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7","download_json":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7.json","view_paper":"https://pith.science/paper/IPDYF7WA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.05301&json=true","fetch_graph":"https://pith.science/api/pith-number/IPDYF7WAL2JQY73ECA6M6ZKLS7/graph.json","fetch_events":"https://pith.science/api/pith-number/IPDYF7WAL2JQY73ECA6M6ZKLS7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7/action/storage_attestation","attest_author":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7/action/author_attestation","sign_citation":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7/action/citation_signature","submit_replication":"https://pith.science/pith/IPDYF7WAL2JQY73ECA6M6ZKLS7/action/replication_record"}},"created_at":"2026-05-17T23:38:49.853333+00:00","updated_at":"2026-05-17T23:38:49.853333+00:00"}