{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GEQACNLEPUKNOFWXP4OHTVKV6D","short_pith_number":"pith:GEQACNLE","schema_version":"1.0","canonical_sha256":"31200135647d14d716d77f1c79d555f0f86d271fb0de62ca45c335e998a24af2","source":{"kind":"arxiv","id":"2306.02224","version":1},"attestation_state":"computed","paper":{"title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Hui Yang, Sifu Yue, Yunzhong He","submitted_at":"2023-06-04T01:07:20Z","abstract_excerpt":"Auto-GPT is an autonomous agent that leverages recent advancements in adapting Large Language Models (LLMs) for decision-making tasks. While there has been a growing interest in Auto-GPT stypled agents, questions remain regarding the effectiveness and flexibility of Auto-GPT in solving real-world decision-making tasks. Its limited capability for real-world engagement and the absence of benchmarks contribute to these uncertainties. In this paper, we present a comprehensive benchmark study of Auto-GPT styled agents in decision-making tasks that simulate real-world scenarios. Our aim is to gain d"},"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":"2306.02224","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-06-04T01:07:20Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fe592830912fdc8e2a57423c9208a66ffae6eaa7b76310585ec6f0f712606bee","abstract_canon_sha256":"9131e596a96dfc0a32be381195391867cab37768d5fe65e86104bf3a27bf77d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:14.461448Z","signature_b64":"bLIGQsLIMgRYzVX/1LY2NtUHyM9ZJZdSf0XUbSvywdP5JhdUWb47FoRB2zDMDLBHplkMsJ2ZVZRq4PpYT3zqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"31200135647d14d716d77f1c79d555f0f86d271fb0de62ca45c335e998a24af2","last_reissued_at":"2026-07-05T06:17:14.461041Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:14.461041Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Auto-GPT for Online Decision Making: Benchmarks and Additional Opinions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Hui Yang, Sifu Yue, Yunzhong He","submitted_at":"2023-06-04T01:07:20Z","abstract_excerpt":"Auto-GPT is an autonomous agent that leverages recent advancements in adapting Large Language Models (LLMs) for decision-making tasks. While there has been a growing interest in Auto-GPT stypled agents, questions remain regarding the effectiveness and flexibility of Auto-GPT in solving real-world decision-making tasks. Its limited capability for real-world engagement and the absence of benchmarks contribute to these uncertainties. In this paper, we present a comprehensive benchmark study of Auto-GPT styled agents in decision-making tasks that simulate real-world scenarios. Our aim is to gain d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02224","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/2306.02224/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":"2306.02224","created_at":"2026-07-05T06:17:14.461098+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.02224v1","created_at":"2026-07-05T06:17:14.461098+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02224","created_at":"2026-07-05T06:17:14.461098+00:00"},{"alias_kind":"pith_short_12","alias_value":"GEQACNLEPUKN","created_at":"2026-07-05T06:17:14.461098+00:00"},{"alias_kind":"pith_short_16","alias_value":"GEQACNLEPUKNOFWX","created_at":"2026-07-05T06:17:14.461098+00:00"},{"alias_kind":"pith_short_8","alias_value":"GEQACNLE","created_at":"2026-07-05T06:17:14.461098+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":26,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.23472","citing_title":"Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22082","citing_title":"CodeTeam: An LLM-Powered Multi-Agent Framework for Repository-Level Code Generation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05874","citing_title":"Evaluating Stochastic Collapse and Implicit Bias in Multimodal Large Language Models","ref_index":78,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01803","citing_title":"OctoT2I: A Self-Evolving Agentic Text-to-Image Router","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31478","citing_title":"One Reflection Is Not Enough: Self-Correcting Autonomous Research via Multi-Hypothesis Failure Attribution","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13893","citing_title":"InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2312.10997","citing_title":"Retrieval-Augmented Generation for Large Language Models: A Survey","ref_index":107,"is_internal_anchor":false},{"citing_arxiv_id":"2411.15594","citing_title":"A Survey on LLM-as-a-Judge","ref_index":187,"is_internal_anchor":false},{"citing_arxiv_id":"2504.12482","citing_title":"Agentic AI Optimisation (AAIO): what it is, how it works, why it matters, and how to deal with it","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":143,"is_internal_anchor":false},{"citing_arxiv_id":"2605.19035","citing_title":"Trustworthy Agent Network: Trust in Agent Networks Must Be Baked In, Not Bolted On","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21236","citing_title":"AgentBound: Securing Execution Boundaries of AI Agents","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2512.08935","citing_title":"From Script to Stage: Automating Experimental Design for Social Simulations with LLMs","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2511.00739","citing_title":"Towards Understanding, Analyzing, and Optimizing Agentic AI Execution: A CPU-Centric Perspective","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2312.13771","citing_title":"AppAgent: Multimodal Agents as Smartphone Users","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2401.16158","citing_title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2311.12983","citing_title":"GAIA: a benchmark for General AI Assistants","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03308","citing_title":"Revisiting the Travel Planning Capabilities of Large Language Models","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26805","citing_title":"Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26805","citing_title":"Bian Que: An Agentic Framework with Flexible Skill Arrangement for Online System Operations","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23472","citing_title":"Escher-Loop: Mutual Evolution by Closed-Loop Self-Referential Optimization","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18500","citing_title":"QRAFTI: An Agentic Framework for Empirical Research in Quantitative Finance","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06839","citing_title":"LLM-Guided Open Hypothesis Learning from Autonomous Scanning Probe Microscopy Experiments","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13536","citing_title":"Don't Let AI Agents YOLO Your Files: Shifting Information and Control to Filesystems for Agent Safety and Autonomy","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16646","citing_title":"Agentic Frameworks for Reasoning Tasks: An Empirical Study","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D","json":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D.json","graph_json":"https://pith.science/api/pith-number/GEQACNLEPUKNOFWXP4OHTVKV6D/graph.json","events_json":"https://pith.science/api/pith-number/GEQACNLEPUKNOFWXP4OHTVKV6D/events.json","paper":"https://pith.science/paper/GEQACNLE"},"agent_actions":{"view_html":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D","download_json":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D.json","view_paper":"https://pith.science/paper/GEQACNLE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.02224&json=true","fetch_graph":"https://pith.science/api/pith-number/GEQACNLEPUKNOFWXP4OHTVKV6D/graph.json","fetch_events":"https://pith.science/api/pith-number/GEQACNLEPUKNOFWXP4OHTVKV6D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D/action/storage_attestation","attest_author":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D/action/author_attestation","sign_citation":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D/action/citation_signature","submit_replication":"https://pith.science/pith/GEQACNLEPUKNOFWXP4OHTVKV6D/action/replication_record"}},"created_at":"2026-07-05T06:17:14.461098+00:00","updated_at":"2026-07-05T06:17:14.461098+00:00"}