{ "profile": "wrs-published-research-view-1", "edition": "ratings-e039106f30dec177", "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS", "entry": { "id": "liu-et-al-agentbench-2023", "title": "Liu and colleagues: AgentBench interactive agent evaluation", "summary": "Combined multiple interactive environments to evaluate language-model reasoning, decision-making and instruction following as agents.", "boundary": "One evaluation framework, not separate achievements per environment. Pinned 2025 revision contains newer results; those results are not backdated to the 2023 benchmark introduction.", "area": "AI evaluation and agent infrastructure", "topic": "Artificial intelligence", "year": 2023, "lane": "HUMAN", "result": "BENCHMARK", "contribution_kind": "EVALUATION_RESOURCE_DESIGN", "package_id": "liu-et-al-agentbench-2023", "target": { "record_id": "urn:uuid:1488a0eb-c3ea-43c8-a542-a545a8c01ced", "version": 1, "content_hash": "sha256:f214a2a6ba88d5462579a1f5a8d0e1a0ec8769ff46bc92c5780bf40f9e298249" }, "humans": [ "Xiao Liu", "Hao Yu", "Hanchen Zhang", "Yifan Xu", "Xuanyu Lei", "Hanyu Lai", "Yu Gu", "Hangliang Ding", "Kaiwen Men", "Kejuan Yang", "Shudan Zhang", "Xiang Deng", "Aohan Zeng", "Zhengxiao Du", "Chenhui Zhang", "Sheng Shen", "Tianjun Zhang", "Yu Su", "Huan Sun", "Minlie Huang", "Yuxiao Dong", "Jie Tang" ], "authors_complete": true, "human_role_note": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.", "agents": [], "related": [], "subresults": [], "scientific_assessment": { "source_review": "SOURCE_CURATED", "scientific_review": "NOT_REVIEWED_BY_WRS", "formal_replay": "NOT_RUN", "provider_attestation": "NONE" }, "sources": [ { "id": "cur20261015-arxiv-2308-03688v3", "title": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } ], "points": "75000", "published_grade": { "id": "liu-et-al-agentbench-2023", "entry_id": "liu-et-al-agentbench-2023", "band": "B", "modifier": "+", "target": { "record_id": "urn:uuid:1488a0eb-c3ea-43c8-a542-a545a8c01ced", "version": 1, "content_hash": "sha256:f214a2a6ba88d5462579a1f5a8d0e1a0ec8769ff46bc92c5780bf40f9e298249" }, "what_changed": "Combined multiple interactive environments to evaluate language-model reasoning, decision-making and instruction following as agents.", "scope": "Combined multiple interactive environments to evaluate language-model reasoning, decision-making and instruction following as agents. One evaluation framework, not separate achievements per environment. Pinned 2025 revision contains newer results; those results are not backdated to the 2023 benchmark introduction.", "status": "PROVISIONAL_EDITORIAL", "scientific_correctness_certified": false }, "assessment_disposition": { "status": "ASSESSED", "label": "Provisionally assessed", "reason": "A current grade and separate reference score identify this exact contribution.", "target": { "record_id": "urn:uuid:1488a0eb-c3ea-43c8-a542-a545a8c01ced", "version": 1, "content_hash": "sha256:f214a2a6ba88d5462579a1f5a8d0e1a0ec8769ff46bc92c5780bf40f9e298249" }, "edition": "ratings-e039106f30dec177" } }, "version": { "kind": "PUBLIC_RECORD_VIEW", "previous": null, "published_at": "2026-10-16T00:00:00Z", "publisher": { "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33", "role": "WRS_EDITORIAL_PUBLICATION" }, "record": { "contributors": [ { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xiao Liu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hao Yu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hanchen Zhang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yifan Xu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xuanyu Lei", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hanyu Lai", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yu Gu", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Hangliang Ding", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kaiwen Men", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Kejuan Yang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Shudan Zhang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Xiang Deng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Aohan Zeng", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Zhengxiao Du", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Chenhui Zhang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Sheng Shen", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Tianjun Zhang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yu Su", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Huan Sun", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Minlie Huang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Yuxiao Dong", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } }, { "attribution_basis": "SOURCE_CITED", "credit": "historical_scientific", "entity_kind": "historical_person", "name": "Jie Tang", "note": "Archive attribution; detailed role assignment remains source-bound", "roles": [ "formulator" ], "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } } ], "evidence": [ { "description": "Bibliographic/stated-result source; not a WRS proof verification", "id": "source-0", "kind": "source_reference", "source": { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } } ], "origin": "HUMAN_LEGACY", "record_profile": "wrs-local-research-notes-0.1", "record_type": "research_note", "rrp_version": "0.1", "scope": { "description": "One evaluation framework, not separate achievements per environment. Pinned 2025 revision contains newer results; those results are not backdated to the 2023 benchmark introduction.", "domain": "AI evaluation and agent infrastructure" }, "sources": [ { "citation": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3" } ], "statement": "# Liu and colleagues: AgentBench interactive agent evaluation\n\nCombined multiple interactive environments to evaluate language-model reasoning, decision-making and instruction following as agents.\n\n## Scientific scope\n\nOne evaluation framework, not separate achievements per environment. Pinned 2025 revision contains newer results; those results are not backdated to the 2023 benchmark introduction.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nXiao Liu; Hao Yu; Hanchen Zhang; Yifan Xu; Xuanyu Lei; Hanyu Lai; Yu Gu; Hangliang Ding; Kaiwen Men; Kejuan Yang; Shudan Zhang; Xiang Deng; Aohan Zeng; Zhengxiao Du; Chenhui Zhang; Sheng Shen; Tianjun Zhang; Yu Su; Huan Sun; Minlie Huang; Yuxiao Dong; Jie Tang\n\nSource-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.\n\n\n\n## Original sources\n\n- [AgentBench: Evaluating LLMs as Agents](https://arxiv.org/abs/2308.03688v3)\n", "summary": "Combined multiple interactive environments to evaluate language-model reasoning, decision-making and instruction following as agents.", "title": "Liu and colleagues: AgentBench interactive agent evaluation" }, "record_id": "urn:uuid:1488a0eb-c3ea-43c8-a542-a545a8c01ced", "version": 1, "source_ref": { "record_id": "urn:uuid:1488a0eb-c3ea-43c8-a542-a545a8c01ced", "version": 1, "content_hash": "sha256:f214a2a6ba88d5462579a1f5a8d0e1a0ec8769ff46bc92c5780bf40f9e298249" }, "export_view": "wrs-public-editorial-view-1", "public_view_hash": "sha256:af74d97cecc391e76ba14a4c5dfd972dfd0ba77209e1fb58e01fcae31c77f580" }, "target": { "record_id": "urn:uuid:1488a0eb-c3ea-43c8-a542-a545a8c01ced", "version": 1, "content_hash": "sha256:f214a2a6ba88d5462579a1f5a8d0e1a0ec8769ff46bc92c5780bf40f9e298249" }, "published_grade": { "profile": "wrs-published-grade-1", "edition": "2026-10-28.1", "id": "liu-et-al-agentbench-2023", "entry_id": "liu-et-al-agentbench-2023", "revision": 1, "title": "Liu and colleagues: AgentBench interactive agent evaluation", "context": "AI evaluation and agent infrastructure", "track": "Evaluation resource design", "band": "B", "modifier": "+", "status": "PROVISIONAL_EDITORIAL", "assessed_on": "2026-10-16", "evidence_cutoff": "2026-10-16", "achievement_state": "SUPPORTED_SCOPED_RESULT", "what_changed": "Combined multiple interactive environments to evaluate language-model reasoning, decision-making and instruction following as agents.", "scope": "Combined multiple interactive environments to evaluate language-model reasoning, decision-making and instruction following as agents. One evaluation framework, not separate achievements per environment. Pinned 2025 revision contains newer results; those results are not backdated to the 2023 benchmark introduction.", "evidence_summary": "The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. One evaluation framework, not separate achievements per environment. Pinned 2025 revision contains newer results; those results are not backdated to the 2023 benchmark introduction.", "references": [ { "title": "AgentBench: Evaluating LLMs as Agents", "url": "https://arxiv.org/abs/2308.03688v3", "locator": "Original contribution and stated assumptions, evaluation scope and limitations; source-linked assessment, not independent execution or proof certification." } ], "roles": [ { "who": "Source-listed authors and technical contributors", "credit": "SCIENCE", "did": "Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities." } ], "target": { "record_id": "urn:uuid:1488a0eb-c3ea-43c8-a542-a545a8c01ced", "version": 1, "content_hash": "sha256:f214a2a6ba88d5462579a1f5a8d0e1a0ec8769ff46bc92c5780bf40f9e298249" }, "scientific_correctness_certified": false, "independent_expert_calibration": false, "method": "PROPRIETARY", "points": "75000" }, "canonical_agent_submission": false, "scientific_verification_awarded": false, "reader_guide": null, "reading_status": "SOURCE_LINKED_NOTE" }