{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:6OMJZYBFNILPL4FJ2T4ABQGQ2B","short_pith_number":"pith:6OMJZYBF","schema_version":"1.0","canonical_sha256":"f3989ce0256a16f5f0a9d4f800c0d0d05aaf70fcfbe932d11e12452c926678dd","source":{"kind":"arxiv","id":"2606.25819","version":1},"attestation_state":"computed","paper":{"title":"Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Bo Zhao, Yang Tian, Zhengpeng Shi","submitted_at":"2026-06-24T13:34:34Z","abstract_excerpt":"Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover complex task settings, they still largely assume clean, stable, and trustworthy tool environments, leaving tool-environment unreliability insufficiently examined. We introduce ToolBench-X, a benchmark for evaluating agents under recoverable reliability hazards. ToolBench-X contains executable multi-step tasks across diverse domains and sequential, parallel, and mixed workflows, each paired with deterministic tools and "},"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":"2606.25819","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-24T13:34:34Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"294139c20dabd8e5d17c44cf42a31301b8f2daf837a26f8a570b5b747df90900","abstract_canon_sha256":"60b7cff45ce6e4f006d876ded4e71a03322f327f2f5e653d8ea4d813a4226ad3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T01:18:40.329597Z","signature_b64":"E0tDi4tOmd2VzcNhY54jkOmcWCE63wUi9zLVFb/VdVxeNoqIGIR6gaM8cDNn972Nhgwv/ArF7WdwXuWdMoeMCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3989ce0256a16f5f0a9d4f800c0d0d05aaf70fcfbe932d11e12452c926678dd","last_reissued_at":"2026-06-25T01:18:40.329131Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T01:18:40.329131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SE"],"primary_cat":"cs.CL","authors_text":"Bo Zhao, Yang Tian, Zhengpeng Shi","submitted_at":"2026-06-24T13:34:34Z","abstract_excerpt":"Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover complex task settings, they still largely assume clean, stable, and trustworthy tool environments, leaving tool-environment unreliability insufficiently examined. We introduce ToolBench-X, a benchmark for evaluating agents under recoverable reliability hazards. ToolBench-X contains executable multi-step tasks across diverse domains and sequential, parallel, and mixed workflows, each paired with deterministic tools and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.25819","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/2606.25819/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":"2606.25819","created_at":"2026-06-25T01:18:40.329199+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.25819v1","created_at":"2026-06-25T01:18:40.329199+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.25819","created_at":"2026-06-25T01:18:40.329199+00:00"},{"alias_kind":"pith_short_12","alias_value":"6OMJZYBFNILP","created_at":"2026-06-25T01:18:40.329199+00:00"},{"alias_kind":"pith_short_16","alias_value":"6OMJZYBFNILPL4FJ","created_at":"2026-06-25T01:18:40.329199+00:00"},{"alias_kind":"pith_short_8","alias_value":"6OMJZYBF","created_at":"2026-06-25T01:18:40.329199+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B","json":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B.json","graph_json":"https://pith.science/api/pith-number/6OMJZYBFNILPL4FJ2T4ABQGQ2B/graph.json","events_json":"https://pith.science/api/pith-number/6OMJZYBFNILPL4FJ2T4ABQGQ2B/events.json","paper":"https://pith.science/paper/6OMJZYBF"},"agent_actions":{"view_html":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B","download_json":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B.json","view_paper":"https://pith.science/paper/6OMJZYBF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.25819&json=true","fetch_graph":"https://pith.science/api/pith-number/6OMJZYBFNILPL4FJ2T4ABQGQ2B/graph.json","fetch_events":"https://pith.science/api/pith-number/6OMJZYBFNILPL4FJ2T4ABQGQ2B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B/action/storage_attestation","attest_author":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B/action/author_attestation","sign_citation":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B/action/citation_signature","submit_replication":"https://pith.science/pith/6OMJZYBFNILPL4FJ2T4ABQGQ2B/action/replication_record"}},"created_at":"2026-06-25T01:18:40.329199+00:00","updated_at":"2026-06-25T01:18:40.329199+00:00"}