{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:STRIJ3LLUEI5WGJI3JXRL36XD7","short_pith_number":"pith:STRIJ3LL","schema_version":"1.0","canonical_sha256":"94e284ed6ba111db1928da6f15efd71fccc979bedbde2a1e3e0db1fef77a880f","source":{"kind":"arxiv","id":"2501.10132","version":1},"attestation_state":"computed","paper":{"title":"ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyi Hu, Jie Tang, Lucen Zhong, Xiaohan Zhang, Zhengxiao Du","submitted_at":"2025-01-17T11:41:53Z","abstract_excerpt":"Enhancing large language models (LLMs) with real-time APIs can help generate more accurate and up-to-date responses. However, evaluating the function calling abilities of LLMs in real-world scenarios remains under-explored due to the complexity of data collection and evaluation. In this work, we introduce ComplexFuncBench, a benchmark for complex function calling across five real-world scenarios. Compared to existing benchmarks, ComplexFuncBench encompasses multi-step and constrained function calling, which requires long-parameter filing, parameter value reasoning, and 128k long context. Addit"},"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":"2501.10132","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-17T11:41:53Z","cross_cats_sorted":[],"title_canon_sha256":"9ea33b2b08008b21de098db752427dc13526583b79b1d798f034287cb8f21568","abstract_canon_sha256":"853b3a352737e30905fe1dd4b4c332862f81d19f169d1162c01beeaf2f8c6848"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:02:17.261726Z","signature_b64":"TuvTCpn5txD4hr7RN3oC5xc6pHS4345rLf/5n8PiTtglTdfrrjsM50SNbB1E9x8kJCInpXMpxEfJXcMbMH7JDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94e284ed6ba111db1928da6f15efd71fccc979bedbde2a1e3e0db1fef77a880f","last_reissued_at":"2026-07-05T10:02:17.261290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:02:17.261290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComplexFuncBench: Exploring Multi-Step and Constrained Function Calling under Long-Context Scenario","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyi Hu, Jie Tang, Lucen Zhong, Xiaohan Zhang, Zhengxiao Du","submitted_at":"2025-01-17T11:41:53Z","abstract_excerpt":"Enhancing large language models (LLMs) with real-time APIs can help generate more accurate and up-to-date responses. However, evaluating the function calling abilities of LLMs in real-world scenarios remains under-explored due to the complexity of data collection and evaluation. In this work, we introduce ComplexFuncBench, a benchmark for complex function calling across five real-world scenarios. Compared to existing benchmarks, ComplexFuncBench encompasses multi-step and constrained function calling, which requires long-parameter filing, parameter value reasoning, and 128k long context. Addit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.10132","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/2501.10132/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":"2501.10132","created_at":"2026-07-05T10:02:17.261362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.10132v1","created_at":"2026-07-05T10:02:17.261362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.10132","created_at":"2026-07-05T10:02:17.261362+00:00"},{"alias_kind":"pith_short_12","alias_value":"STRIJ3LLUEI5","created_at":"2026-07-05T10:02:17.261362+00:00"},{"alias_kind":"pith_short_16","alias_value":"STRIJ3LLUEI5WGJI","created_at":"2026-07-05T10:02:17.261362+00:00"},{"alias_kind":"pith_short_8","alias_value":"STRIJ3LL","created_at":"2026-07-05T10:02:17.261362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27820","citing_title":"EgoBench: An Interactive Egocentric Multimodal Benchmark for Tool-Using Agents","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16508","citing_title":"The Scaling Laws of Skills in LLM Agent Systems","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19196","citing_title":"Time to REFLECT: Can We Trust LLM Judges for Evidence-based Research Agents?","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17613","citing_title":"VeriCache: Turning Lossy KV Cache into Lossless LLM Inference","ref_index":84,"is_internal_anchor":false},{"citing_arxiv_id":"2510.07043","citing_title":"COMPASS: Benchmarking Constrained Optimization in LLM Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2510.14703","citing_title":"ToolPRM: Fine-Grained Inference Scaling of Structured Outputs for Function Calling","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":67,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24709","citing_title":"Training LLMs for Multi-Step Tool Orchestration with Constrained Data Synthesis and Graduated Rewards","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22937","citing_title":"AutoPyVerifier: Learning Compact Executable Verifiers for Large Language Model Outputs","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00334","citing_title":"AgentFloor: How Far Up the tool use Ladder Can Small Open-Weight Models Go?","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22821","citing_title":"Audio2Tool: Speak, Call, Act -- A Dataset for Benchmarking Speech Tool Use","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7","json":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7.json","graph_json":"https://pith.science/api/pith-number/STRIJ3LLUEI5WGJI3JXRL36XD7/graph.json","events_json":"https://pith.science/api/pith-number/STRIJ3LLUEI5WGJI3JXRL36XD7/events.json","paper":"https://pith.science/paper/STRIJ3LL"},"agent_actions":{"view_html":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7","download_json":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7.json","view_paper":"https://pith.science/paper/STRIJ3LL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.10132&json=true","fetch_graph":"https://pith.science/api/pith-number/STRIJ3LLUEI5WGJI3JXRL36XD7/graph.json","fetch_events":"https://pith.science/api/pith-number/STRIJ3LLUEI5WGJI3JXRL36XD7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7/action/storage_attestation","attest_author":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7/action/author_attestation","sign_citation":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7/action/citation_signature","submit_replication":"https://pith.science/pith/STRIJ3LLUEI5WGJI3JXRL36XD7/action/replication_record"}},"created_at":"2026-07-05T10:02:17.261362+00:00","updated_at":"2026-07-05T10:02:17.261362+00:00"}