{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JF56VO5SN7R5KDSFCMO66SQKFB","short_pith_number":"pith:JF56VO5S","schema_version":"1.0","canonical_sha256":"497beabbb26fe3d50e45131def4a0a284707c38969bdd9453daeb961d7b14061","source":{"kind":"arxiv","id":"2507.21407","version":2},"attestation_state":"computed","paper":{"title":"Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guibin Zhang, Kun Wang, Shirui Pan, Shiyuan Li, Yixin Liu","submitted_at":"2025-07-29T00:27:12Z","abstract_excerpt":"Autonomous agents based on large language models (LLMs) have demonstrated impressive capabilities in a wide range of applications, including web navigation, software development, and embodied control. While most LLMs are limited in several key agentic procedures, such as reliable planning, long-term memory, tool management, and multi-agent coordination, graphs can serve as a powerful auxiliary structure to enhance structure, continuity, and coordination in complex agent workflows. Given the rapid growth and fragmentation of research on Graph-augmented LLM Agents (GLA), this paper offers a time"},"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":"2507.21407","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-07-29T00:27:12Z","cross_cats_sorted":[],"title_canon_sha256":"514b6965cf3bef442a0ced652f4bf5ea7e54d757f86653aee837b9da0c5227a7","abstract_canon_sha256":"3d3e6608a736d36e0ceb3af12e2ce6566640ba819468310459fb6fa9e571d739"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:04.346550Z","signature_b64":"Zl80zoY56IaQWRYx79edAbmXohD6vHxPZHaM1OJ34PWqpUyhYNKKPxxnd3tvx86xbTzTaEG9wd7OFsmPxx3lAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"497beabbb26fe3d50e45131def4a0a284707c38969bdd9453daeb961d7b14061","last_reissued_at":"2026-07-05T12:02:04.345992Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:04.345992Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guibin Zhang, Kun Wang, Shirui Pan, Shiyuan Li, Yixin Liu","submitted_at":"2025-07-29T00:27:12Z","abstract_excerpt":"Autonomous agents based on large language models (LLMs) have demonstrated impressive capabilities in a wide range of applications, including web navigation, software development, and embodied control. While most LLMs are limited in several key agentic procedures, such as reliable planning, long-term memory, tool management, and multi-agent coordination, graphs can serve as a powerful auxiliary structure to enhance structure, continuity, and coordination in complex agent workflows. Given the rapid growth and fragmentation of research on Graph-augmented LLM Agents (GLA), this paper offers a time"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.21407","kind":"arxiv","version":2},"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/2507.21407/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":"2507.21407","created_at":"2026-07-05T12:02:04.346053+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.21407v2","created_at":"2026-07-05T12:02:04.346053+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.21407","created_at":"2026-07-05T12:02:04.346053+00:00"},{"alias_kind":"pith_short_12","alias_value":"JF56VO5SN7R5","created_at":"2026-07-05T12:02:04.346053+00:00"},{"alias_kind":"pith_short_16","alias_value":"JF56VO5SN7R5KDSF","created_at":"2026-07-05T12:02:04.346053+00:00"},{"alias_kind":"pith_short_8","alias_value":"JF56VO5S","created_at":"2026-07-05T12:02:04.346053+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2508.08127","citing_title":"BlindGuard: Safeguarding LLM-based Multi-Agent Systems under Unknown Attacks","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.13564","citing_title":"Memory in the Age of AI Agents","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11378","citing_title":"From Agent Loops to Structured Graphs:A Scheduler-Theoretic Framework for LLM Agent Execution","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB","json":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB.json","graph_json":"https://pith.science/api/pith-number/JF56VO5SN7R5KDSFCMO66SQKFB/graph.json","events_json":"https://pith.science/api/pith-number/JF56VO5SN7R5KDSFCMO66SQKFB/events.json","paper":"https://pith.science/paper/JF56VO5S"},"agent_actions":{"view_html":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB","download_json":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB.json","view_paper":"https://pith.science/paper/JF56VO5S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.21407&json=true","fetch_graph":"https://pith.science/api/pith-number/JF56VO5SN7R5KDSFCMO66SQKFB/graph.json","fetch_events":"https://pith.science/api/pith-number/JF56VO5SN7R5KDSFCMO66SQKFB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB/action/storage_attestation","attest_author":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB/action/author_attestation","sign_citation":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB/action/citation_signature","submit_replication":"https://pith.science/pith/JF56VO5SN7R5KDSFCMO66SQKFB/action/replication_record"}},"created_at":"2026-07-05T12:02:04.346053+00:00","updated_at":"2026-07-05T12:02:04.346053+00:00"}