{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V47ROJF7ZZE2SKRW7DLDPQSQBI","short_pith_number":"pith:V47ROJF7","schema_version":"1.0","canonical_sha256":"af3f1724bfce49a92a36f8d637c2500a059d2b29b7ee2b1971748104e8982f4f","source":{"kind":"arxiv","id":"2401.13178","version":2},"attestation_state":"computed","paper":{"title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chang Ma, Cheng Yang, Junlei Zhang, Junxian He, Lingpeng Kong, Yaohui Jin, Yujiu Yang, Zhenzhong Lan, Zhihao Zhu","submitted_at":"2024-01-24T01:51:00Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial challenges. A primary obstacle is the benchmarking of agent performance across diverse scenarios within a unified framework, especially in maintaining partially-observable environments and ensuring multi-round interactions. Moreover, current evaluation frameworks mostly focus on the final success rate, revealing few insights during the process and failing to provid"},"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":"2401.13178","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-01-24T01:51:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6334d597b955ac933c0b34035fd2242d9aaff7e96508756ab202466bf4713b7a","abstract_canon_sha256":"69b84116481db88ae1e1bde621373cb412d3365e8b1e6c145cb9b3d8cab80b2f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:28.192407Z","signature_b64":"yiqkVzIBG9H17EBzg0qoDnQLRMdDYUHNK1feeNVzKDtaknM9dkrAwTeK+LucQuzPneor6mzd2eq6nTR8MxtIBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af3f1724bfce49a92a36f8d637c2500a059d2b29b7ee2b1971748104e8982f4f","last_reissued_at":"2026-07-05T09:53:28.191874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:28.191874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentBoard: An Analytical Evaluation Board of Multi-turn LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chang Ma, Cheng Yang, Junlei Zhang, Junxian He, Lingpeng Kong, Yaohui Jin, Yujiu Yang, Zhenzhong Lan, Zhihao Zhu","submitted_at":"2024-01-24T01:51:00Z","abstract_excerpt":"Evaluating Large Language Models (LLMs) as general-purpose agents is essential for understanding their capabilities and facilitating their integration into practical applications. However, the evaluation process presents substantial challenges. A primary obstacle is the benchmarking of agent performance across diverse scenarios within a unified framework, especially in maintaining partially-observable environments and ensuring multi-round interactions. Moreover, current evaluation frameworks mostly focus on the final success rate, revealing few insights during the process and failing to provid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.13178","kind":"arxiv","version":2},"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/2401.13178/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":"2401.13178","created_at":"2026-07-05T09:53:28.191930+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.13178v2","created_at":"2026-07-05T09:53:28.191930+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.13178","created_at":"2026-07-05T09:53:28.191930+00:00"},{"alias_kind":"pith_short_12","alias_value":"V47ROJF7ZZE2","created_at":"2026-07-05T09:53:28.191930+00:00"},{"alias_kind":"pith_short_16","alias_value":"V47ROJF7ZZE2SKRW","created_at":"2026-07-05T09:53:28.191930+00:00"},{"alias_kind":"pith_short_8","alias_value":"V47ROJF7","created_at":"2026-07-05T09:53:28.191930+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":17,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11686","citing_title":"Layer-Isolated Evaluation: Gating the Deterministic Scaffold of a Production LLM Agent with a No-LLM, Regression-Locked Test Harness","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10315","citing_title":"Catching One in Five: LLM-as-Judge Blind Spots in Production Multi-Turn Transaction Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05670","citing_title":"Do More Agents Help? Controlled and Protocol-Aligned Evaluation of LLM Agent Workflows","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01961","citing_title":"AutoMedBench: Towards Medical AutoResearch with Agentic AI Models","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19743","citing_title":"EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20530","citing_title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.20530","citing_title":"AgentAtlas: Beyond Outcome Leaderboards for LLM Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19743","citing_title":"EngiAI: A Multi-Agent Framework and Benchmark Suite for LLM-Driven Engineering Design","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2506.04565","citing_title":"From Standalone LLMs to Integrated Intelligence: A Survey of Compound Al Systems","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2602.09514","citing_title":"EcoGym: Evaluating LLMs for Long-Horizon Plan-and-Execute in Interactive Economies","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2501.09686","citing_title":"Towards Large Reasoning Models: A Survey of Reinforced Reasoning with Large Language Models","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14865","citing_title":"Holistic Evaluation and Failure Diagnosis of AI Agents","ref_index":18,"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":154,"is_internal_anchor":false},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2404.07972","citing_title":"OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13564","citing_title":"Memory in the Age of AI Agents","ref_index":278,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07054","citing_title":"Sell More, Play Less: Benchmarking LLM Realistic Selling Skill","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI","json":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI.json","graph_json":"https://pith.science/api/pith-number/V47ROJF7ZZE2SKRW7DLDPQSQBI/graph.json","events_json":"https://pith.science/api/pith-number/V47ROJF7ZZE2SKRW7DLDPQSQBI/events.json","paper":"https://pith.science/paper/V47ROJF7"},"agent_actions":{"view_html":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI","download_json":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI.json","view_paper":"https://pith.science/paper/V47ROJF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.13178&json=true","fetch_graph":"https://pith.science/api/pith-number/V47ROJF7ZZE2SKRW7DLDPQSQBI/graph.json","fetch_events":"https://pith.science/api/pith-number/V47ROJF7ZZE2SKRW7DLDPQSQBI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI/action/storage_attestation","attest_author":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI/action/author_attestation","sign_citation":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI/action/citation_signature","submit_replication":"https://pith.science/pith/V47ROJF7ZZE2SKRW7DLDPQSQBI/action/replication_record"}},"created_at":"2026-07-05T09:53:28.191930+00:00","updated_at":"2026-07-05T09:53:28.191930+00:00"}