{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BOLK5DSGLHZPDJ2EI6B2BYCQQA","short_pith_number":"pith:BOLK5DSG","schema_version":"1.0","canonical_sha256":"0b96ae8e4659f2f1a7444783a0e0508006a337057abfb064aa8c1347d8ce79ea","source":{"kind":"arxiv","id":"2505.20231","version":2},"attestation_state":"computed","paper":{"title":"MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baojun Wang, Bingbing Wang, Bin Liang, Jeff Z. Pan, Kam-Fai Wong, Lin Gui, Ruifeng Xu, Yang He, Yiming Du, Zhongyang Li","submitted_at":"2025-05-26T17:10:43Z","abstract_excerpt":"Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods are primarily based on semantic similarity, overlooking task intent and reducing task coherence in multi-session dialogues. To address this challenge, we introduce MemGuide, a two-stage framework for intent-driven memory selection. (1) Intent-Aligned Retrieval matches the current dialogue context with stored intent descriptions in the memory bank, retrieving QA-f"},"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":"2505.20231","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T17:10:43Z","cross_cats_sorted":[],"title_canon_sha256":"7032aedc72c051f5699fcb0bcf4bc8cbecc29012ee8d194b0c291bbca29335d6","abstract_canon_sha256":"b309454d587b9e70f5e7c3fca205e4756645bb332eca50aeb3720a66c6395d5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:03.599119Z","signature_b64":"AF8UgaW0dENf10MBmb7pgxC4Qvp9/wi+3u74JZgdhe5H3Gj4Rudz1rPsFww7tWgROy+uqHIl5QT//PUumMflDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0b96ae8e4659f2f1a7444783a0e0508006a337057abfb064aa8c1347d8ce79ea","last_reissued_at":"2026-07-05T11:53:03.598523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:03.598523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MemGuide: Intent-Driven Memory Selection for Goal-Oriented Multi-Session LLM Agents","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baojun Wang, Bingbing Wang, Bin Liang, Jeff Z. Pan, Kam-Fai Wong, Lin Gui, Ruifeng Xu, Yang He, Yiming Du, Zhongyang Li","submitted_at":"2025-05-26T17:10:43Z","abstract_excerpt":"Modern task-oriented dialogue (TOD) systems increasingly rely on large language model (LLM) agents, leveraging Retrieval-Augmented Generation (RAG) and long-context capabilities for long-term memory utilization. However, these methods are primarily based on semantic similarity, overlooking task intent and reducing task coherence in multi-session dialogues. To address this challenge, we introduce MemGuide, a two-stage framework for intent-driven memory selection. (1) Intent-Aligned Retrieval matches the current dialogue context with stored intent descriptions in the memory bank, retrieving QA-f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20231","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/2505.20231/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":"2505.20231","created_at":"2026-07-05T11:53:03.598614+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20231v2","created_at":"2026-07-05T11:53:03.598614+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20231","created_at":"2026-07-05T11:53:03.598614+00:00"},{"alias_kind":"pith_short_12","alias_value":"BOLK5DSGLHZP","created_at":"2026-07-05T11:53:03.598614+00:00"},{"alias_kind":"pith_short_16","alias_value":"BOLK5DSGLHZPDJ2E","created_at":"2026-07-05T11:53:03.598614+00:00"},{"alias_kind":"pith_short_8","alias_value":"BOLK5DSG","created_at":"2026-07-05T11:53:03.598614+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.14906","citing_title":"MemLens: Benchmarking Multimodal Long-Term Memory in Large Vision-Language Models","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18421","citing_title":"EvoMemBench: Benchmarking Agent Memory from a Self-Evolving Perspective","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03312","citing_title":"MemFlow: Intent-Driven Memory Orchestration for Small Language Model Agents","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11628","citing_title":"Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA","json":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA.json","graph_json":"https://pith.science/api/pith-number/BOLK5DSGLHZPDJ2EI6B2BYCQQA/graph.json","events_json":"https://pith.science/api/pith-number/BOLK5DSGLHZPDJ2EI6B2BYCQQA/events.json","paper":"https://pith.science/paper/BOLK5DSG"},"agent_actions":{"view_html":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA","download_json":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA.json","view_paper":"https://pith.science/paper/BOLK5DSG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20231&json=true","fetch_graph":"https://pith.science/api/pith-number/BOLK5DSGLHZPDJ2EI6B2BYCQQA/graph.json","fetch_events":"https://pith.science/api/pith-number/BOLK5DSGLHZPDJ2EI6B2BYCQQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA/action/storage_attestation","attest_author":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA/action/author_attestation","sign_citation":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA/action/citation_signature","submit_replication":"https://pith.science/pith/BOLK5DSGLHZPDJ2EI6B2BYCQQA/action/replication_record"}},"created_at":"2026-07-05T11:53:03.598614+00:00","updated_at":"2026-07-05T11:53:03.598614+00:00"}