{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:KNIJAXB6MDJFZDETICH2KWX3QQ","short_pith_number":"pith:KNIJAXB6","schema_version":"1.0","canonical_sha256":"5350905c3e60d25c8c93408fa55afb8410c859eb94976c1cdde33af0c2abc1d9","source":{"kind":"arxiv","id":"2308.05960","version":1},"attestation_state":"computed","paper":{"title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Devansh Arpit, Huan Wang, Jianguo Zhang, Juan Carlos Niebles, Le Xue, Phil Mui, Ran Xu, Rithesh Murthy, Shelby Heinecke, Silvio Savarese, Weiran Yao, Yihao Feng, Zeyuan Chen, Zhiwei Liu","submitted_at":"2023-08-11T06:37:54Z","abstract_excerpt":"The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs). An LAA is able to generate actions with its core LLM and interact with environments, which facilitates the ability to resolve complex tasks by conditioning on past interactions such as observations and actions. Since the investigation of LAA is still very recent, limited explorations are available. Therefore, we provide a comprehensive comparison of LAA in terms of both agent architectures and LLM backbones. Additionally, we propose a new strategy to orchestrate m"},"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":"2308.05960","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-11T06:37:54Z","cross_cats_sorted":[],"title_canon_sha256":"70f6f2faa3585c7c98dc0245ce4aab4f14925f37be01933e798c469dc172fd10","abstract_canon_sha256":"4d801661ef3e29e693f291ac759060feae8d5b9d127e0368f7820672d767f0e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:21.192190Z","signature_b64":"7CziWSZz6PJTdq2XyDqm77HzQzdc8AXZxmHG0gkNk9VX8bHYUo2p7bz3GxRMNFXdR7pomHXVR7KN5FguZunIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5350905c3e60d25c8c93408fa55afb8410c859eb94976c1cdde33af0c2abc1d9","last_reissued_at":"2026-07-05T06:40:21.191734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:21.191734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BOLAA: Benchmarking and Orchestrating LLM-augmented Autonomous Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Caiming Xiong, Devansh Arpit, Huan Wang, Jianguo Zhang, Juan Carlos Niebles, Le Xue, Phil Mui, Ran Xu, Rithesh Murthy, Shelby Heinecke, Silvio Savarese, Weiran Yao, Yihao Feng, Zeyuan Chen, Zhiwei Liu","submitted_at":"2023-08-11T06:37:54Z","abstract_excerpt":"The massive successes of large language models (LLMs) encourage the emerging exploration of LLM-augmented Autonomous Agents (LAAs). An LAA is able to generate actions with its core LLM and interact with environments, which facilitates the ability to resolve complex tasks by conditioning on past interactions such as observations and actions. Since the investigation of LAA is still very recent, limited explorations are available. Therefore, we provide a comprehensive comparison of LAA in terms of both agent architectures and LLM backbones. Additionally, we propose a new strategy to orchestrate m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.05960","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/2308.05960/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":"2308.05960","created_at":"2026-07-05T06:40:21.191800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.05960v1","created_at":"2026-07-05T06:40:21.191800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.05960","created_at":"2026-07-05T06:40:21.191800+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNIJAXB6MDJF","created_at":"2026-07-05T06:40:21.191800+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNIJAXB6MDJFZDET","created_at":"2026-07-05T06:40:21.191800+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNIJAXB6","created_at":"2026-07-05T06:40:21.191800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06157","citing_title":"LLM Agents for Deliberative Collaboration: A Study on Joint Decision Making Under Partial Observability","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2502.03814","citing_title":"Large Language Models for Multi-Robot Systems: A Survey","ref_index":76,"is_internal_anchor":false},{"citing_arxiv_id":"2310.02170","citing_title":"A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration","ref_index":12,"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":106,"is_internal_anchor":false},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2403.07718","citing_title":"WorkArena: How Capable Are Web Agents at Solving Common Knowledge Work Tasks?","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2311.12983","citing_title":"GAIA: a benchmark for General AI Assistants","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07462","citing_title":"The Moltbook Files: A Harmless Slopocalypse or Humanity's Last Experiment","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ","json":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ.json","graph_json":"https://pith.science/api/pith-number/KNIJAXB6MDJFZDETICH2KWX3QQ/graph.json","events_json":"https://pith.science/api/pith-number/KNIJAXB6MDJFZDETICH2KWX3QQ/events.json","paper":"https://pith.science/paper/KNIJAXB6"},"agent_actions":{"view_html":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ","download_json":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ.json","view_paper":"https://pith.science/paper/KNIJAXB6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.05960&json=true","fetch_graph":"https://pith.science/api/pith-number/KNIJAXB6MDJFZDETICH2KWX3QQ/graph.json","fetch_events":"https://pith.science/api/pith-number/KNIJAXB6MDJFZDETICH2KWX3QQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ/action/storage_attestation","attest_author":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ/action/author_attestation","sign_citation":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ/action/citation_signature","submit_replication":"https://pith.science/pith/KNIJAXB6MDJFZDETICH2KWX3QQ/action/replication_record"}},"created_at":"2026-07-05T06:40:21.191800+00:00","updated_at":"2026-07-05T06:40:21.191800+00:00"}