{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ERIKW5NULSALI755C3PSGKZLWH","short_pith_number":"pith:ERIKW5NU","schema_version":"1.0","canonical_sha256":"2450ab75b45c80b47fbd16df232b2bb1e0d6268eebcbc765369a9b81d81dcaf3","source":{"kind":"arxiv","id":"2308.04026","version":1},"attestation_state":"computed","paper":{"title":"AgentSims: An Open-Source Sandbox for Large Language Model Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aochi Zhang, Haoran Zhao, Huqiuyue Ping, Jiaju Lin, Qin Chen, Yiting Wu","submitted_at":"2023-08-08T03:59:28Z","abstract_excerpt":"With ChatGPT-like large language models (LLM) prevailing in the community, how to evaluate the ability of LLMs is an open question. Existing evaluation methods suffer from following shortcomings: (1) constrained evaluation abilities, (2) vulnerable benchmarks, (3) unobjective metrics. We suggest that task-based evaluation, where LLM agents complete tasks in a simulated environment, is a one-for-all solution to solve above problems. We present AgentSims, an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in. Researchers can bui"},"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":"2308.04026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T03:59:28Z","cross_cats_sorted":[],"title_canon_sha256":"7faacf8b82f0305d56dff5477166d62da1e2d896e09bdb2cba727e1c6bb9d3f0","abstract_canon_sha256":"f7076233fa76c0efa749232d30a8f0778eb357d17fe321248582a4d703a2181a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:39:21.220730Z","signature_b64":"IfLGyrVvhX/d+VK+r6AD4hLYZRx4gzx4cmG12TbOn7V5KtRIWqpaMfziYiU2BCVaIrZX6fy6GIeNektio0z0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2450ab75b45c80b47fbd16df232b2bb1e0d6268eebcbc765369a9b81d81dcaf3","last_reissued_at":"2026-07-05T06:39:21.220225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:39:21.220225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AgentSims: An Open-Source Sandbox for Large Language Model Evaluation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Aochi Zhang, Haoran Zhao, Huqiuyue Ping, Jiaju Lin, Qin Chen, Yiting Wu","submitted_at":"2023-08-08T03:59:28Z","abstract_excerpt":"With ChatGPT-like large language models (LLM) prevailing in the community, how to evaluate the ability of LLMs is an open question. Existing evaluation methods suffer from following shortcomings: (1) constrained evaluation abilities, (2) vulnerable benchmarks, (3) unobjective metrics. We suggest that task-based evaluation, where LLM agents complete tasks in a simulated environment, is a one-for-all solution to solve above problems. We present AgentSims, an easy-to-use infrastructure for researchers from all disciplines to test the specific capacities they are interested in. Researchers can bui"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04026","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/2308.04026/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":"2308.04026","created_at":"2026-07-05T06:39:21.220282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.04026v1","created_at":"2026-07-05T06:39:21.220282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04026","created_at":"2026-07-05T06:39:21.220282+00:00"},{"alias_kind":"pith_short_12","alias_value":"ERIKW5NULSAL","created_at":"2026-07-05T06:39:21.220282+00:00"},{"alias_kind":"pith_short_16","alias_value":"ERIKW5NULSALI755","created_at":"2026-07-05T06:39:21.220282+00:00"},{"alias_kind":"pith_short_8","alias_value":"ERIKW5NU","created_at":"2026-07-05T06:39:21.220282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":16,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06815","citing_title":"Behavioral Privacy Leakage in Agentic Negotiation: Formalizing and Mitigating Inference Attacks via Randomized Policies","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26883","citing_title":"EconSimulacra: A Digital Twin Platform of Socio-Economic Systems Powered by LLM Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08367","citing_title":"Emergence World: A Platform for Evaluating Long-Horizon Multi-Agent Autonomy","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26883","citing_title":"EconSimulacra: A Digital Twin Platform of Socio-Economic Systems Powered by LLM Agents","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25815","citing_title":"Behind EvoMap: Characterizing a Self-Evolving Agent-to-Agent Collaboration Network","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02293","citing_title":"AI as a Tool for Simulation-Based Experiments in Literary Studies","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2505.11336","citing_title":"XtraGPT: Context-Aware and Controllable Academic Paper Revision via Human-AI Collaboration","ref_index":79,"is_internal_anchor":false},{"citing_arxiv_id":"2506.23978","citing_title":"LLM Agents Are the Antidote to Walled Gardens","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2401.05561","citing_title":"TrustLLM: Trustworthiness in Large Language Models","ref_index":137,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":69,"is_internal_anchor":false},{"citing_arxiv_id":"2410.07283","citing_title":"Prompt Infection: LLM-to-LLM Prompt Injection within Multi-Agent Systems","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2406.13352","citing_title":"AgentDojo: A Dynamic Environment to Evaluate Prompt Injection Attacks and Defenses for LLM Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2311.12983","citing_title":"GAIA: a benchmark for General AI Assistants","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2309.07864","citing_title":"The Rise and Potential of Large Language Model Based Agents: A Survey","ref_index":175,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07462","citing_title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","ref_index":68,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH","json":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH.json","graph_json":"https://pith.science/api/pith-number/ERIKW5NULSALI755C3PSGKZLWH/graph.json","events_json":"https://pith.science/api/pith-number/ERIKW5NULSALI755C3PSGKZLWH/events.json","paper":"https://pith.science/paper/ERIKW5NU"},"agent_actions":{"view_html":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH","download_json":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH.json","view_paper":"https://pith.science/paper/ERIKW5NU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.04026&json=true","fetch_graph":"https://pith.science/api/pith-number/ERIKW5NULSALI755C3PSGKZLWH/graph.json","fetch_events":"https://pith.science/api/pith-number/ERIKW5NULSALI755C3PSGKZLWH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH/action/storage_attestation","attest_author":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH/action/author_attestation","sign_citation":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH/action/citation_signature","submit_replication":"https://pith.science/pith/ERIKW5NULSALI755C3PSGKZLWH/action/replication_record"}},"created_at":"2026-07-05T06:39:21.220282+00:00","updated_at":"2026-07-05T06:39:21.220282+00:00"}