{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6P5ERI27Y7OGORTWVPPGQOHWOA","short_pith_number":"pith:6P5ERI27","schema_version":"1.0","canonical_sha256":"f3fa48a35fc7dc674676abde6838f67005370723255dd0b47839f800d418f5ed","source":{"kind":"arxiv","id":"2501.11067","version":1},"attestation_state":"computed","paper":{"title":"IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Elad Levi, Ilan Kadar","submitted_at":"2025-01-19T14:58:35Z","abstract_excerpt":"Large Language Models (LLMs) are transforming artificial intelligence, evolving into task-oriented systems capable of autonomous planning and execution. One of the primary applications of LLMs is conversational AI systems, which must navigate multi-turn dialogues, integrate domain-specific APIs, and adhere to strict policy constraints. However, evaluating these agents remains a significant challenge, as traditional methods fail to capture the complexity and variability of real-world interactions. We introduce IntellAgent, a scalable, open-source multi-agent framework designed to evaluate conve"},"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":"2501.11067","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-19T14:58:35Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7ca61ce66b910231de29ce0aeb411065452effff17121b498e48fb73905b1dd7","abstract_canon_sha256":"77c09e00b54726b06cad25ace5f62a175859499f45dd23729a4575ba25ea9bac"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:03:02.856359Z","signature_b64":"zRBhFgn9gc8h5oDAJVq54hKGGmA56Uk6gHmyfrxATr0mno6T5i9PvDZYhoR5vagN+l8+8ZC6ki0OJloGGX7OBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f3fa48a35fc7dc674676abde6838f67005370723255dd0b47839f800d418f5ed","last_reissued_at":"2026-07-05T10:03:02.855929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:03:02.855929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"IntellAgent: A Multi-Agent Framework for Evaluating Conversational AI Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Elad Levi, Ilan Kadar","submitted_at":"2025-01-19T14:58:35Z","abstract_excerpt":"Large Language Models (LLMs) are transforming artificial intelligence, evolving into task-oriented systems capable of autonomous planning and execution. One of the primary applications of LLMs is conversational AI systems, which must navigate multi-turn dialogues, integrate domain-specific APIs, and adhere to strict policy constraints. However, evaluating these agents remains a significant challenge, as traditional methods fail to capture the complexity and variability of real-world interactions. We introduce IntellAgent, a scalable, open-source multi-agent framework designed to evaluate conve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11067","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/2501.11067/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":"2501.11067","created_at":"2026-07-05T10:03:02.855983+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11067v1","created_at":"2026-07-05T10:03:02.855983+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11067","created_at":"2026-07-05T10:03:02.855983+00:00"},{"alias_kind":"pith_short_12","alias_value":"6P5ERI27Y7OG","created_at":"2026-07-05T10:03:02.855983+00:00"},{"alias_kind":"pith_short_16","alias_value":"6P5ERI27Y7OGORTW","created_at":"2026-07-05T10:03:02.855983+00:00"},{"alias_kind":"pith_short_8","alias_value":"6P5ERI27","created_at":"2026-07-05T10:03:02.855983+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17829","citing_title":"Interactive Evaluation Requires a Design Science","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20857","citing_title":"Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2506.07982","citing_title":"$\\tau^2$-Bench: Evaluating Conversational Agents in a Dual-Control Environment","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06334","citing_title":"MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06111","citing_title":"AgentCE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA","json":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA.json","graph_json":"https://pith.science/api/pith-number/6P5ERI27Y7OGORTWVPPGQOHWOA/graph.json","events_json":"https://pith.science/api/pith-number/6P5ERI27Y7OGORTWVPPGQOHWOA/events.json","paper":"https://pith.science/paper/6P5ERI27"},"agent_actions":{"view_html":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA","download_json":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA.json","view_paper":"https://pith.science/paper/6P5ERI27","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11067&json=true","fetch_graph":"https://pith.science/api/pith-number/6P5ERI27Y7OGORTWVPPGQOHWOA/graph.json","fetch_events":"https://pith.science/api/pith-number/6P5ERI27Y7OGORTWVPPGQOHWOA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA/action/storage_attestation","attest_author":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA/action/author_attestation","sign_citation":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA/action/citation_signature","submit_replication":"https://pith.science/pith/6P5ERI27Y7OGORTWVPPGQOHWOA/action/replication_record"}},"created_at":"2026-07-05T10:03:02.855983+00:00","updated_at":"2026-07-05T10:03:02.855983+00:00"}