{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FCOWCQG2DZ2ZPAHPDTIDI4FP6C","short_pith_number":"pith:FCOWCQG2","schema_version":"1.0","canonical_sha256":"289d6140da1e759780ef1cd03470aff092b88d6b25847fca221ab744efead9d5","source":{"kind":"arxiv","id":"2503.19213","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Large Language Model Agents for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Murong Yue","submitted_at":"2025-03-24T23:39:44Z","abstract_excerpt":"This paper surveys the development of large language model (LLM)-based agents for question answering (QA). Traditional agents face significant limitations, including substantial data requirements and difficulty in generalizing to new environments. LLM-based agents address these challenges by leveraging LLMs as their core reasoning engine. These agents achieve superior QA results compared to traditional QA pipelines and naive LLM QA systems by enabling interaction with external environments. We systematically review the design of LLM agents in the context of QA tasks, organizing our discussion "},"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":"2503.19213","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-24T23:39:44Z","cross_cats_sorted":["cs.AI","cs.HC"],"title_canon_sha256":"abbaf6dca07527de919acfb21c47f853015f4cbf0a9a0da8e083be7cd0493d52","abstract_canon_sha256":"264830426b3396eae8c9cc94286f042c60738957203096e02d35c524ee48efcc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:38:51.293968Z","signature_b64":"ddyjXkLUjRnwzzSvpILZB76zkuUD4XcQCwGEqseaBvEKKGB6WqoVjjGGGFlUN2liPVtjlGY69tUyFEO27UFaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"289d6140da1e759780ef1cd03470aff092b88d6b25847fca221ab744efead9d5","last_reissued_at":"2026-07-05T10:38:51.293556Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:38:51.293556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Large Language Model Agents for Question Answering","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC"],"primary_cat":"cs.CL","authors_text":"Murong Yue","submitted_at":"2025-03-24T23:39:44Z","abstract_excerpt":"This paper surveys the development of large language model (LLM)-based agents for question answering (QA). Traditional agents face significant limitations, including substantial data requirements and difficulty in generalizing to new environments. LLM-based agents address these challenges by leveraging LLMs as their core reasoning engine. These agents achieve superior QA results compared to traditional QA pipelines and naive LLM QA systems by enabling interaction with external environments. We systematically review the design of LLM agents in the context of QA tasks, organizing our discussion "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19213","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/2503.19213/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":"2503.19213","created_at":"2026-07-05T10:38:51.293608+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19213v1","created_at":"2026-07-05T10:38:51.293608+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19213","created_at":"2026-07-05T10:38:51.293608+00:00"},{"alias_kind":"pith_short_12","alias_value":"FCOWCQG2DZ2Z","created_at":"2026-07-05T10:38:51.293608+00:00"},{"alias_kind":"pith_short_16","alias_value":"FCOWCQG2DZ2ZPAHP","created_at":"2026-07-05T10:38:51.293608+00:00"},{"alias_kind":"pith_short_8","alias_value":"FCOWCQG2","created_at":"2026-07-05T10:38:51.293608+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25404","citing_title":"HEART: Coordination of Heterogeneous Expert Agents for Physically Grounded Robotic Task Planning","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.22906","citing_title":"From Fragments to Paths: Task-Level Context Recovery for Large Industrial Codebases","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23965","citing_title":"LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31064","citing_title":"Fighting Numerical Hallucinations via Data-centric Compilation for Online Financial QA","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31308","citing_title":"Benchmarking Large Language Models on Floating-Point Error Classification","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23965","citing_title":"LGMT: Logic-Grounded Metamorphic Testing for Evaluating the Reasoning Reliability of LLMs","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26178","citing_title":"ATOM: Instantiating Budget-Controllable Multi-Agent Collaboration via Nucleus-Electron Hierarchy","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07731","citing_title":"Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2601.16432","citing_title":"iPDB -- Optimizing Semantic SQL Queries","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07731","citing_title":"Benchmarking EngGPT2-16B-A3B against Comparable Italian and International Open-source LLMs","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19820","citing_title":"KnowPilot: Your Knowledge-Driven Copilot for Domain Tasks","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C","json":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C.json","graph_json":"https://pith.science/api/pith-number/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/graph.json","events_json":"https://pith.science/api/pith-number/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/events.json","paper":"https://pith.science/paper/FCOWCQG2"},"agent_actions":{"view_html":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C","download_json":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C.json","view_paper":"https://pith.science/paper/FCOWCQG2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19213&json=true","fetch_graph":"https://pith.science/api/pith-number/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/graph.json","fetch_events":"https://pith.science/api/pith-number/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/action/storage_attestation","attest_author":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/action/author_attestation","sign_citation":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/action/citation_signature","submit_replication":"https://pith.science/pith/FCOWCQG2DZ2ZPAHPDTIDI4FP6C/action/replication_record"}},"created_at":"2026-07-05T10:38:51.293608+00:00","updated_at":"2026-07-05T10:38:51.293608+00:00"}