{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:EEKNOJNH3NPIO6ZU6RQPGVKXJX","short_pith_number":"pith:EEKNOJNH","schema_version":"1.0","canonical_sha256":"2114d725a7db5e877b34f460f355574dc44db64e817c18b70a0ec9cb6b6aa131","source":{"kind":"arxiv","id":"2605.10787","version":2},"attestation_state":"computed","paper":{"title":"ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM agents reach under 60 percent success on interdependent tool tasks where humans hit 90 percent.","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Hongyang Chen, Longyue Wang, Weihua Luo, Xue Yang, Yuanyang Li","submitted_at":"2026-05-11T16:20:51Z","abstract_excerpt":"Current LLM agents are proficient at calling isolated APIs but struggle with the \"last mile\" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental noise. We introduce $\\textbf{ComplexMCP}$, a benchmark designed to evaluate agents in these rigorous conditions. Built on the Model Context Protocol (MCP), $\\textbf{ComplexMCP}$ provides over 300 meticulously tested tools derived from 7 stateful sandboxes, ranging from office suites to financial systems. Unlike existing datasets, our benchmark utilizes a see"},"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":"2605.10787","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T16:20:51Z","cross_cats_sorted":["cs.SE"],"title_canon_sha256":"fd2bd41c287548fd92863647a6abcb8f2ff287080bf077adc3083aeb001322a7","abstract_canon_sha256":"a68599b15e9a0582b3aef49b4ae36f640f5b839bcf4e3d08437117843ec2004a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:27.540192Z","signature_b64":"R7o3VBG1/wueQqfa56Q4rnpjA4aAtLWyorxJZCnUWFnL/r5JpgFSd39UnLqpvy+dEfp9S+pSFKq4MzaYcBo4Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2114d725a7db5e877b34f460f355574dc44db64e817c18b70a0ec9cb6b6aa131","last_reissued_at":"2026-05-21T01:04:27.539391Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:27.539391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox","license":"http://creativecommons.org/licenses/by/4.0/","headline":"LLM agents reach under 60 percent success on interdependent tool tasks where humans hit 90 percent.","cross_cats":["cs.SE"],"primary_cat":"cs.AI","authors_text":"Hongyang Chen, Longyue Wang, Weihua Luo, Xue Yang, Yuanyang Li","submitted_at":"2026-05-11T16:20:51Z","abstract_excerpt":"Current LLM agents are proficient at calling isolated APIs but struggle with the \"last mile\" of commercial software automation. In real-world scenarios, tools are not independent; they are atomic, interdependent, and prone to environmental noise. We introduce $\\textbf{ComplexMCP}$, a benchmark designed to evaluate agents in these rigorous conditions. Built on the Model Context Protocol (MCP), $\\textbf{ComplexMCP}$ provides over 300 meticulously tested tools derived from 7 stateful sandboxes, ranging from office suites to financial systems. Unlike existing datasets, our benchmark utilizes a see"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"even top-tier models fail to exceed a 60% success rate, far trailing human performance 90%. Granular trajectory analysis identifies three fundamental bottlenecks: (1) tool retrieval saturation as action spaces scale; (2) over-confidence, where agents skip essential environment verifications; and (3) strategic defeatism, a tendency to rationalize failure rather than pursuing recovery.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The 7 stateful sandboxes and 300 tools derived from them sufficiently represent the interdependent, noisy conditions of real-world commercial software automation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"ComplexMCP benchmark shows current LLM agents achieve at most 60% success on interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"LLM agents reach under 60 percent success on interdependent tool tasks where humans hit 90 percent.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"8057dbadd909034fb9f5b0fd4661a5d8d4f7110efb64319b3712927e8c22d70f"},"source":{"id":"2605.10787","kind":"arxiv","version":2},"verdict":{"id":"3b30be21-c64d-419d-8e6d-93bdba03522f","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T04:37:47.107372Z","strongest_claim":"even top-tier models fail to exceed a 60% success rate, far trailing human performance 90%. Granular trajectory analysis identifies three fundamental bottlenecks: (1) tool retrieval saturation as action spaces scale; (2) over-confidence, where agents skip essential environment verifications; and (3) strategic defeatism, a tendency to rationalize failure rather than pursuing recovery.","one_line_summary":"ComplexMCP benchmark shows current LLM agents achieve at most 60% success on interdependent tool tasks versus 90% for humans, due to tool retrieval saturation, over-confidence, and strategic defeatism.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The 7 stateful sandboxes and 300 tools derived from them sufficiently represent the interdependent, noisy conditions of real-world commercial software automation.","pith_extraction_headline":"LLM agents reach under 60 percent success on interdependent tool tasks where humans hit 90 percent."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10787/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:22:00.382797Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:35:51.574811Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T10:31:17.789485Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T08:58:52.075793Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"24642f0bbdb1fe908881af6cae8eeb19b84ccbd618d70c09890213eae89c513e"},"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":"2605.10787","created_at":"2026-05-21T01:04:27.539480+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10787v2","created_at":"2026-05-21T01:04:27.539480+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10787","created_at":"2026-05-21T01:04:27.539480+00:00"},{"alias_kind":"pith_short_12","alias_value":"EEKNOJNH3NPI","created_at":"2026-05-21T01:04:27.539480+00:00"},{"alias_kind":"pith_short_16","alias_value":"EEKNOJNH3NPIO6ZU","created_at":"2026-05-21T01:04:27.539480+00:00"},{"alias_kind":"pith_short_8","alias_value":"EEKNOJNH","created_at":"2026-05-21T01:04:27.539480+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/EEKNOJNH3NPIO6ZU6RQPGVKXJX","json":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX.json","graph_json":"https://pith.science/api/pith-number/EEKNOJNH3NPIO6ZU6RQPGVKXJX/graph.json","events_json":"https://pith.science/api/pith-number/EEKNOJNH3NPIO6ZU6RQPGVKXJX/events.json","paper":"https://pith.science/paper/EEKNOJNH"},"agent_actions":{"view_html":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX","download_json":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX.json","view_paper":"https://pith.science/paper/EEKNOJNH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10787&json=true","fetch_graph":"https://pith.science/api/pith-number/EEKNOJNH3NPIO6ZU6RQPGVKXJX/graph.json","fetch_events":"https://pith.science/api/pith-number/EEKNOJNH3NPIO6ZU6RQPGVKXJX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX/action/storage_attestation","attest_author":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX/action/author_attestation","sign_citation":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX/action/citation_signature","submit_replication":"https://pith.science/pith/EEKNOJNH3NPIO6ZU6RQPGVKXJX/action/replication_record"}},"created_at":"2026-05-21T01:04:27.539480+00:00","updated_at":"2026-05-21T01:04:27.539480+00:00"}