{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:INL6MKT7B6Q2UCBRAKMSXPAXG4","short_pith_number":"pith:INL6MKT7","schema_version":"1.0","canonical_sha256":"4357e62a7f0fa1aa083102992bbc173731d133e9f0da9ab0b256a0f55ada4629","source":{"kind":"arxiv","id":"2505.13328","version":1},"attestation_state":"computed","paper":{"title":"Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongru Wang, Huan Zhang, Jeff Z. Pan, Jianqiao Lu, Kam-Fai Wong, Nan Hu, Wenyu Huang, Yuanhao Xi, Yufei Wang, Zeming Liu","submitted_at":"2025-05-19T16:36:13Z","abstract_excerpt":"Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications. To fulfill this gap, we propose \\texttt{DialogTool}, a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use, across six key tasks in three stages: 1) \\textit{tool creation}; 2) \\textit{tool utilization}: tool awareness, tool selection, tool execution;"},"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":"2505.13328","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-19T16:36:13Z","cross_cats_sorted":[],"title_canon_sha256":"89bbdc489cff7444ae7db40d255bd69188b4010427ca5ebdf3c8d272335920a7","abstract_canon_sha256":"a1412da2d5260163d3155952f39eaf7f2c75e3c50d2c4b43a88a5faf5ab0a1da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:28.573426Z","signature_b64":"6RL1o4iT5lq6qgj6AFyTPUgNhkJOMsi4P0r8BSkt4VqtUzBot0wXwK/YGTGfxXCzKEfe3xQKnbh5QBY5V55rBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4357e62a7f0fa1aa083102992bbc173731d133e9f0da9ab0b256a0f55ada4629","last_reissued_at":"2026-07-05T11:05:28.572920Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:28.572920Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Stateful Tool Use in Multi-Turn Dialogues: Benchmarks and Challenges","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hongru Wang, Huan Zhang, Jeff Z. Pan, Jianqiao Lu, Kam-Fai Wong, Nan Hu, Wenyu Huang, Yuanhao Xi, Yufei Wang, Zeming Liu","submitted_at":"2025-05-19T16:36:13Z","abstract_excerpt":"Existing benchmarks that assess Language Models (LMs) as Language Agents (LAs) for tool use primarily focus on stateless, single-turn interactions or partial evaluations, such as tool selection in a single turn, overlooking the inherent stateful nature of interactions in multi-turn applications. To fulfill this gap, we propose \\texttt{DialogTool}, a multi-turn dialogue dataset with stateful tool interactions considering the whole life cycle of tool use, across six key tasks in three stages: 1) \\textit{tool creation}; 2) \\textit{tool utilization}: tool awareness, tool selection, tool execution;"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13328","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/2505.13328/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":"2505.13328","created_at":"2026-07-05T11:05:28.572982+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13328v1","created_at":"2026-07-05T11:05:28.572982+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13328","created_at":"2026-07-05T11:05:28.572982+00:00"},{"alias_kind":"pith_short_12","alias_value":"INL6MKT7B6Q2","created_at":"2026-07-05T11:05:28.572982+00:00"},{"alias_kind":"pith_short_16","alias_value":"INL6MKT7B6Q2UCBR","created_at":"2026-07-05T11:05:28.572982+00:00"},{"alias_kind":"pith_short_8","alias_value":"INL6MKT7","created_at":"2026-07-05T11:05:28.572982+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.03499","citing_title":"WeClawArena: An Auditable Sandbox and Benchmark for Cross-User Agents Collaboration and Security in Human-Centered Agent Networks","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4","json":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4.json","graph_json":"https://pith.science/api/pith-number/INL6MKT7B6Q2UCBRAKMSXPAXG4/graph.json","events_json":"https://pith.science/api/pith-number/INL6MKT7B6Q2UCBRAKMSXPAXG4/events.json","paper":"https://pith.science/paper/INL6MKT7"},"agent_actions":{"view_html":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4","download_json":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4.json","view_paper":"https://pith.science/paper/INL6MKT7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13328&json=true","fetch_graph":"https://pith.science/api/pith-number/INL6MKT7B6Q2UCBRAKMSXPAXG4/graph.json","fetch_events":"https://pith.science/api/pith-number/INL6MKT7B6Q2UCBRAKMSXPAXG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4/action/storage_attestation","attest_author":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4/action/author_attestation","sign_citation":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4/action/citation_signature","submit_replication":"https://pith.science/pith/INL6MKT7B6Q2UCBRAKMSXPAXG4/action/replication_record"}},"created_at":"2026-07-05T11:05:28.572982+00:00","updated_at":"2026-07-05T11:05:28.572982+00:00"}