{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DHSNRXFAVGIVEYYUVJFMXZ4IGZ","short_pith_number":"pith:DHSNRXFA","schema_version":"1.0","canonical_sha256":"19e4d8dca0a991526314aa4acbe788365451116a399e085414978c61bd5c6d90","source":{"kind":"arxiv","id":"2504.18765","version":3},"attestation_state":"computed","paper":{"title":"A Vision for Auto Research with LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengwei Liu, Chong Wang, Jiayue Cao, Jingquan Ge, Kun Wang, Lyuye Zhang, Ming-Ming Cheng, Penghai Zhao, Tianlin Li, Xiang Li, Xiaojun Jia, Xingshuai Li, Yang Liu, Yebo Feng, Yihao Huang, Yijia Xu, Yuqiang Sun, Zhengzi Xu, Zhenhong Zhou","submitted_at":"2025-04-26T02:06:10Z","abstract_excerpt":"This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the system spans all major research phases, including literature review, ideation, methodology planning, experimentation, paper writing, peer review response, and dissemination. By addressing issues such as fragmented workflows, uneven methodological expertise, and cognitive overload, the framework offers a systematic and scalable "},"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":"2504.18765","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-04-26T02:06:10Z","cross_cats_sorted":[],"title_canon_sha256":"27e9a5c7d3594c8af7de51055847819494dd87d3304516521165fa3ef9075f30","abstract_canon_sha256":"de444af4adacaa3f9ff533f7810e705b010e3eeac439430a66554acf7d304af4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:53.340473Z","signature_b64":"TqLs/D6dHkrUvG8X8SXdhtVqtEsghuOOR4U+hKSk+zOdDcg/H/25wnynov+YA8/R4fbbMl6A0qnSOBArnDs7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"19e4d8dca0a991526314aa4acbe788365451116a399e085414978c61bd5c6d90","last_reissued_at":"2026-07-05T11:39:53.339919Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:53.339919Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Vision for Auto Research with LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chengwei Liu, Chong Wang, Jiayue Cao, Jingquan Ge, Kun Wang, Lyuye Zhang, Ming-Ming Cheng, Penghai Zhao, Tianlin Li, Xiang Li, Xiaojun Jia, Xingshuai Li, Yang Liu, Yebo Feng, Yihao Huang, Yijia Xu, Yuqiang Sun, Zhengzi Xu, Zhenhong Zhou","submitted_at":"2025-04-26T02:06:10Z","abstract_excerpt":"This paper introduces Agent-Based Auto Research, a structured multi-agent framework designed to automate, coordinate, and optimize the full lifecycle of scientific research. Leveraging the capabilities of large language models (LLMs) and modular agent collaboration, the system spans all major research phases, including literature review, ideation, methodology planning, experimentation, paper writing, peer review response, and dissemination. By addressing issues such as fragmented workflows, uneven methodological expertise, and cognitive overload, the framework offers a systematic and scalable "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18765","kind":"arxiv","version":3},"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/2504.18765/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":"2504.18765","created_at":"2026-07-05T11:39:53.339979+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18765v3","created_at":"2026-07-05T11:39:53.339979+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18765","created_at":"2026-07-05T11:39:53.339979+00:00"},{"alias_kind":"pith_short_12","alias_value":"DHSNRXFAVGIV","created_at":"2026-07-05T11:39:53.339979+00:00"},{"alias_kind":"pith_short_16","alias_value":"DHSNRXFAVGIVEYYU","created_at":"2026-07-05T11:39:53.339979+00:00"},{"alias_kind":"pith_short_8","alias_value":"DHSNRXFA","created_at":"2026-07-05T11:39:53.339979+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26130","citing_title":"Thinking Like a Scientist? A Structural Study of LLM-Generated Research Methods","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30246","citing_title":"Clarus: Coordinating Autonomous Research Agents toward Web-Scale Scientific Collaboration","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28655","citing_title":"AutoScientists: Self-Organizing Agent Teams for Long-Running Scientific Experimentation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2510.13896","citing_title":"GenCellAgent: Generalizable, Training-Free Cellular Image Segmentation via Large Language Model Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2510.16853","citing_title":"Agentic Inequality","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02289","citing_title":"EngiAgent: Fully Connected Coordination of LLM Agents for Solving Open-ended Engineering Problems with Feasible Solutions","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12290","citing_title":"Frontier-Eng: Benchmarking Self-Evolving Agents on Real-World Engineering Tasks with Generative Optimization","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ","json":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ.json","graph_json":"https://pith.science/api/pith-number/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/graph.json","events_json":"https://pith.science/api/pith-number/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/events.json","paper":"https://pith.science/paper/DHSNRXFA"},"agent_actions":{"view_html":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ","download_json":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ.json","view_paper":"https://pith.science/paper/DHSNRXFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18765&json=true","fetch_graph":"https://pith.science/api/pith-number/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/action/storage_attestation","attest_author":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/action/author_attestation","sign_citation":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/action/citation_signature","submit_replication":"https://pith.science/pith/DHSNRXFAVGIVEYYUVJFMXZ4IGZ/action/replication_record"}},"created_at":"2026-07-05T11:39:53.339979+00:00","updated_at":"2026-07-05T11:39:53.339979+00:00"}