{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RFTPJZWKAJ6RZNMXBDGH6L6J3I","short_pith_number":"pith:RFTPJZWK","schema_version":"1.0","canonical_sha256":"8966f4e6ca027d1cb59708cc7f2fc9da0a0bccba8bbe8cc76d50eff147975f27","source":{"kind":"arxiv","id":"2310.12823","version":2},"attestation_state":"computed","paper":{"title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aohan Zeng, Bowen Wang, Jie Tang, Mingdao Liu, Rui Lu, Xiao Liu, Yuxiao Dong","submitted_at":"2023-10-19T15:19:53Z","abstract_excerpt":"Open large language models (LLMs) with great performance in various tasks have significantly advanced the development of LLMs. However, they are far inferior to commercial models such as ChatGPT and GPT-4 when acting as agents to tackle complex tasks in the real world. These agent tasks employ LLMs as the central controller responsible for planning, memorization, and tool utilization, necessitating both fine-grained prompting methods and robust LLMs to achieve satisfactory performance. Though many prompting methods have been proposed to complete particular agent tasks, there is lack of researc"},"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":"2310.12823","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-10-19T15:19:53Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"676e0d32b129ebb3b86c6f23454e1bee86c3f976a5a276d09acaad2b075826a8","abstract_canon_sha256":"37042a17b1fc23282d9b4c86bf2f527403fa60f83a906072f54631b853521d0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:03:32.821221Z","signature_b64":"8yo0Qry9BQMHtV3XhuEMyZzX7owznE9v+VUQLqvKpXNTzSdtNXXsAzUne5+k0VciP8o8cpXRVPVvUTdysWfCCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8966f4e6ca027d1cb59708cc7f2fc9da0a0bccba8bbe8cc76d50eff147975f27","last_reissued_at":"2026-07-05T07:03:32.820665Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:03:32.820665Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentTuning: Enabling Generalized Agent Abilities for LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Aohan Zeng, Bowen Wang, Jie Tang, Mingdao Liu, Rui Lu, Xiao Liu, Yuxiao Dong","submitted_at":"2023-10-19T15:19:53Z","abstract_excerpt":"Open large language models (LLMs) with great performance in various tasks have significantly advanced the development of LLMs. However, they are far inferior to commercial models such as ChatGPT and GPT-4 when acting as agents to tackle complex tasks in the real world. These agent tasks employ LLMs as the central controller responsible for planning, memorization, and tool utilization, necessitating both fine-grained prompting methods and robust LLMs to achieve satisfactory performance. Though many prompting methods have been proposed to complete particular agent tasks, there is lack of researc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.12823","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/2310.12823/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":"2310.12823","created_at":"2026-07-05T07:03:32.820724+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.12823v2","created_at":"2026-07-05T07:03:32.820724+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.12823","created_at":"2026-07-05T07:03:32.820724+00:00"},{"alias_kind":"pith_short_12","alias_value":"RFTPJZWKAJ6R","created_at":"2026-07-05T07:03:32.820724+00:00"},{"alias_kind":"pith_short_16","alias_value":"RFTPJZWKAJ6RZNMX","created_at":"2026-07-05T07:03:32.820724+00:00"},{"alias_kind":"pith_short_8","alias_value":"RFTPJZWK","created_at":"2026-07-05T07:03:32.820724+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25449","citing_title":"Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26935","citing_title":"Where Do CoT Training Gains Land in LLM based Agents?","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26918","citing_title":"Diagnosing Task Insensitivity in Language Agents","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27147","citing_title":"Safe Autoregressive Image Generation with Iterative Self-Improving Codebooks","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21740","citing_title":"Training the Orchestrator: A Supervised Approach to End-to-End PDDL Planning with LLM Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20295","citing_title":"Token-Operations-Oriented Inference Optimization Techniques for Large Models","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11520","citing_title":"ISE: An Execution-Grounded Recipe for Multi-Turn OS-Agent Trajectories","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25449","citing_title":"Reclaim Evaluation: A Lossy Memory Is Worse Than an Empty One","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27632","citing_title":"Yuvion LLM: An Adversarially-Aware Large Language Model for Content And AI Safety","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2506.03610","citing_title":"Orak: A Foundational Benchmark for Training and Evaluating LLM Agents on Diverse Video Games","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15134","citing_title":"The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2510.00568","citing_title":"ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07718","citing_title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2506.15841","citing_title":"MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03512","citing_title":"ActionNex: A Virtual Outage Manager for Cloud Computing","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2402.02716","citing_title":"Understanding the planning of LLM agents: A survey","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":127,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23194","citing_title":"From Coarse to Fine: Self-Adaptive Hierarchical Planning for LLM Agents","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20148","citing_title":"Meta-Tool: Efficient Few-Shot Tool Adaptation for Small Language Models","ref_index":55,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I","json":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I.json","graph_json":"https://pith.science/api/pith-number/RFTPJZWKAJ6RZNMXBDGH6L6J3I/graph.json","events_json":"https://pith.science/api/pith-number/RFTPJZWKAJ6RZNMXBDGH6L6J3I/events.json","paper":"https://pith.science/paper/RFTPJZWK"},"agent_actions":{"view_html":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I","download_json":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I.json","view_paper":"https://pith.science/paper/RFTPJZWK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.12823&json=true","fetch_graph":"https://pith.science/api/pith-number/RFTPJZWKAJ6RZNMXBDGH6L6J3I/graph.json","fetch_events":"https://pith.science/api/pith-number/RFTPJZWKAJ6RZNMXBDGH6L6J3I/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I/action/storage_attestation","attest_author":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I/action/author_attestation","sign_citation":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I/action/citation_signature","submit_replication":"https://pith.science/pith/RFTPJZWKAJ6RZNMXBDGH6L6J3I/action/replication_record"}},"created_at":"2026-07-05T07:03:32.820724+00:00","updated_at":"2026-07-05T07:03:32.820724+00:00"}